Saturday, April 4, 2026

One Song, Many Tongues: On Death, Love, and What Persists


Sometimes I am amazed at how human experience finds a way of manifesting itself in poetry across different languages and cultures. While listening to this Celtic-style song "The Raven", I couldn't help but be reminded of these lines (attributed to Kabir?, my attempt at an english translation and commentary below).


کاگا سب تن کھائیو، چن چن کھائیو ماس

دو نیناں مت کھائیو، انہیں پیا ملن کی آس


آج کہ کال کہ پچھے دن، جنگل ہوئے گا باس

اوپر اوپر پھریں گے، ڈھور چرتے گھاس


پنجر پریم پرکاسیا، انتر بھیا جاس

مکھ کستوری مہکہی، بانی پھوٹی باس


کبیر کہا گر بیو، اس جوبن کی آس

ٹیسو پھول دوس چار، کھنکھر بھئے پلاس


ہاڈ جلے جیوں لاکری، کیس جلیں جیوں گھاس

سب تن جلتا دیکھ کر، بھیا کبیر داس


---


اردو تشریح:


کاگا سب تن کھائیو، چن چن کھائیو ماس: اے کوے (موت/جسم کے ٹکڑے کرنے والے)، میرے پورے جسم کو کھا لے اور چن چن کر گوشت ختم کر دے۔


دو نیناں مت کھائیو، انہیں پیا ملن کی آس: لیکن میری دونوں آنکھیں مت کھانا، کیونکہ ان میں ابھی محبوب سے ملنے کی امید باقی ہے۔


پنجر پریم پرکاسیا، انتر بھیا جاس: جب جسم کے پنجرے میں عشق روشن ہوا، تو اندر کی آگاہی بھی روشن ہو گئی۔


مکھ کستوری مہکہی، بانی پھوٹی باس: اس عشق کی وجہ سے وجود میں خوشبو پیدا ہوئی اور زبان سے مہکتی ہوئی باتیں نکلنے لگیں۔


ہاڈ جلے جیوں لاکری، کیس جلیں جیوں گھاس: آخرکار ہڈیاں لکڑی کی طرح اور بال گھاس کی طرح جل گئے۔


سب تن جلتا دیکھ کر، بھیا کبیر داس: جب پورا جسم فنا ہو گیا تو انسان حقیقی معنوں میں بندگی کی حالت تک پہنچا۔


English interpretation:


O Raven, consume this entire body, pick away every piece of flesh.

But do not touch these two eyes, for they still carry the hope of meeting the beloved.


Today or tomorrow, after a few days, this body will become a dwelling of the wilderness.

Above it, creatures will wander, and cattle will graze upon what remains.


When love illuminated this cage of the body, the inner being became awakened.

The face began to carry a musk-like fragrance, and speech itself became imbued with sweetness.


Kabir says, why cling to the illusion of youth?

Like the palash flower that blooms briefly, all beauty soon turns to dust.


Bones burn like wood, and hair like dry grass.

Seeing the whole body consumed, Kabir became truly a servant, dissolved beyond the self.


---


Lyrics --The Raven


Through the mist I see her wings,

A shadow black where twilight clings.

The raven calls the night to rise,

A song of stars that pierce the skies.


Chorus:

Oh raven, raven, take my soul,

Fly where the endless rivers roll.

Through ancient trees and whispered streams,

Oh raven, raven, carry my dreams.


Her feathers catch the moon's pale fire,

A silent witness to desire.

She knows the secrets I have lost,

Each truth I've hidden, each line I've crossed.


Pre-Chorus:

Oh, tell me where the winds have gone,

And why the earth still hums her song.


(Chorus)


Beneath her wings, the world unwinds,

She sees the threads we leave behind.

No words, no vows, no promises stay,

The raven comes and sweeps them away.


(Chorus)


==


Different languages, different traditions, but the same idea returns:


The body fades, but longing remains.

And somehow, we imagine it carried onward -- by a bird, a shadow, a song.




 

Saturday, December 13, 2025

The allegory of strange loops: A perspective on AI guided cancer research

 The allegory of strange loops: A perspective on AI guided cancer research

By Fayyaz Minhas (With AI editorial support)


I often begin my talks about my research in understanding cancer pathobiology with Plato's allegory of the cave. Prisoners sit chained to a wall, watching shadows cast by unseen objects behind them. They debate the nature of reality by analysing those shadows, unaware of the processes that generate them. In many ways, we as scientists find ourselves in a similar position. We observe measurements, images, molecular readouts, and clinical outcomes. These are shadows cast by deeper biological processes. Our task is not merely to describe the shadows, but to infer the mechanisms that generate them, so that we can intervene meaningfully in the real world.

Modern cancer research is often framed as a choice between levels of description. At one extreme lie molecular profiles such as mutations, gene expression, and epigenetic marks, treated as privileged causes of disease. At the other lie tissue images such as whole slide pathology and spatial maps, treated as rich, high dimensional summaries of downstream phenotypic effects. Increasingly, the proposed solution is multimodality: integrate everything using artificial intelligence, and the truth will emerge.

But multimodality is a tool, not a philosophy. One can be multimodal and still profoundly reductionist.

The deeper problem is not missing data, but how we, particularly as computer scientists, think about causation, explanation, and understanding in biology. Cancer and many other complex pathologies are not poorly understood because we lack modalities. They are poorly understood because we continue to force self organising, non linear systems into explanatory frames designed for linear causation.

Genes explain evolution, not construction

The phrase “it's all in the genes” is deeply ingrained in biological thinking. Richard Dawkins' The Selfish Gene is often taken as support for this idea, but this is a misunderstanding. Genetic determinism is the belief that knowing the genes is sufficient to predict biological outcomes, that DNA functions as a blueprint whose execution yields inevitable form and behaviour. Dawkins does not make this claim. His argument is precise and limited. Genes are replicators, units of evolutionary persistence. They explain why certain traits spread through populations over evolutionary time, much like memes spread culturally. They do not explain how organisms are constructed, how tissues organise, or how disease unfolds dynamically within an individual.

Philip Ball's How Life Works makes this distinction explicit. Genes are not programs or blueprints. They do not encode form directly. Biological order arises from interactions among genes, physical constraints, cellular dynamics, and environmental context. Development, robustness, and pathology are processes rather than executions of code. Form is constructed through interaction, not read out from DNA.

Yet in cancer biology, gene centred thinking quietly hardened into genetic determinism. One gene, one solution narratives flourished, sometimes implicitly and sometimes explicitly. These narratives achieved spectacular success in particular contexts, such as subsets of acute myeloid leukaemia, where single mutations can explain disease mechanisms and enable targeted therapy.

These successes were real, but they were also misleading. They encouraged the belief that cancer in general is a molecular wiring problem waiting to be debugged, perhaps one day to be edited away. Most diseases are not like this. They are not deterministic, linear, or reducible to isolated molecular causes.

Life, order, and the strange loop

My thinking here owes much to Gödel, Escher, Bach and I Am a Strange Loop by Douglas Hofstadter. I did not fully understand these books when I first read them, and I may never fully understand them. This is not a weakness of the books. As Nassim Nicholas Taleb has observed, if a book can be fully understood by a summary, it likely did not need to be written. Books that continue to yield new interpretations upon rereading are often those grappling with genuinely deep ideas.

Hofstadter introduced a way of thinking that has proven indispensable. Complex systems generate meaning and behaviour through circular causation. In a strange loop, higher level patterns emerge from lower level interactions and then act back upon them. The system becomes self referential. Escher's drawings, where hands draw one another or staircases loop back onto themselves, are visual demonstrations of this principle.

This is Hofstadter's account of consciousness, but it is also a powerful account of biology. Cancer, viewed through this lens, is not a simple accumulation of mutations. It is an emergent reorganisation of a tissue level system. It adapts, persists, and exhibits apparent goal directedness. When we say that a tumour invades or that cancer metastasises, we are not invoking intention, but we are not speaking nonsense either. We are describing emergent teleology, behaviour that appears purposeful because it arises from feedback driven organisation.

Order against entropy and the origin of emergence

Where does this apparent purpose come from in life and disease. William James Sidis, in The Animate and the Inanimate, approached this question from a thermodynamic perspective. Sidis suggested that life locally reverses the second law of thermodynamics. This is not correct as literal physics. Living systems do not violate thermodynamic laws. However, Sidis captured something enduring and important. Living systems are non equilibrium systems that maintain and propagate structure against dissipation through continuous flows of energy and information.

This sustained organisation creates feedback loops. These loops stabilise patterns, amplify certain behaviours, and suppress others. Over time, such loops give rise to structures that persist, adapt, and interact. Even pathological life does this. Cancer is not random noise. It is structured, patterned, and persistent, almost like one strange loop interacting destructively with another.

Teleology in biology does not arise from intention but from stability. Patterns that persist appear purposeful because they have survived the dynamics that would otherwise dissolve them.

Cancer emerges at the tissue level

Complex systems often exhibit properties that are more than the sum of their parts. Simple local rules can give rise to complex global behaviour, a principle explored extensively by Stephen Wolfram in A New Kind of Science. Cellular automata governed by trivial rules can suddenly cross thresholds into rich, unpredictable dynamics.

Biology appears to operate in exactly this way. Below certain organisational thresholds, behaviour remains simple and local. Above them, new levels of causation emerge.

This view is formalised in the emergent theory of cancer articulated by Sigston and Williams, who reject the sufficiency of the somatic mutation theory. They argue that cancer is an emergent system arising at the level of the functional tissue unit, not at the level of genes or individual cells.

In this framework, tissue architecture is not a downstream consequence of molecular change but a primary explanatory level. Causation is multi scale and bidirectional. Genes influence tissue organisation, but tissue organisation constrains gene expression, cellular behaviour, and evolutionary trajectories.

This relationship can be formalised statistically and information theoretically. Imaging patterns reduce uncertainty about mutations or cellular states and vice versa, revealing measurable mutual information between morphology and molecular profiles. This statistical dependence enables prediction. Certain architectural patterns correlate with aggressive disease, particular mutations, or coordinated expression programs.

But statistical dependence is not causation, nor does it explain the latent mechanisms that generate both. Diagnosing cancer from genes alone is conceptually incomplete because it ignores the constraints imposed by tissue organisation. Explaining cancer purely from morphology risks mistaking stabilised patterns for primary causes. Both errors arise from collapsing a circular system into a one way explanation.

Images are not explanations either

When I moved from bioinformatics into computational pathology, I initially thought of whole slide images as another downstream layer of molecular events. Over time, this assumption eroded. Computational pathology is too often reduced to machine learning on slides rather than understood as a way to study disease processes themselves using computation, particularly the latent causes that give rise to observed patterns.

There has been substantial work on predicting gene expression or mutations from morphology. These efforts are useful, but the predictions are never perfect. The standard explanations invoke noise, limited datasets, or weak labels. These explanations are convenient but insufficient.

There is growing evidence that mechanical forces and geometry influence gene regulation. Studies have shown that nuclear deformation can alter chromatin organisation and transcriptional programs in colorectal cancer and other systems. Shape affects transcription. If mechanical perturbation of nuclei can regulate genes, then tissue architecture cannot be treated as a passive readout. Form acts back on function, reminiscent of Escher's hands drawing one another.

This is the strange loop again. Genes shape tissue. Tissue reshapes gene expression. The system stabilises around emergent phenotypes that we observe as tumour evolution. The difficulty of predicting molecular states from images is not merely noise or dataset limitation. It reflects the fact that causal prediction is fundamentally harder than anticausal prediction, especially in systems with circular causation, as emphasised by Bernhard Schölkopf and others.

Multimodality is not the point

At this stage, it is tempting to declare multimodal integration as the solution. A more holistic picture is necessary, but multimodality can easily become a fetish. One can integrate images, transcriptomics, and proteomics while still treating one level as ground truth and the others as noisy reflections. This reproduces reductionism under the guise of completeness.

The goal is not to stack modalities. The goal is to change the explanatory frame.

Causality, not comfort

This is where Judea Pearl's The Book of Why becomes essential. Pearl's central argument is that prediction is not explanation. Correlation cannot answer what if questions. Understanding requires causal models that encode interventions, counterfactuals, and feedback.

AI in biology is often asked to be explanatory in a psychological sense, to reassure us, to pacify us, to tell stories that feel intuitive or controllable. But explanatory AI can become an anaesthetic. It can obscure rather than illuminate when it reinforces simplistic narratives.

The task is not to explain cancer in comforting terms, but to reason about it correctly, because lives depend on it.

Rethinking experimentation and evidence

This shift has implications for how we design experiments and therapies. Much of modern biology still revolves around isolating individual cells, increasingly through organoids, perturbing them with drugs, and extrapolating upward. This approach has value, but it remains limited.

As Professor David Epstein once observed, death is a non subjective assessment. Outcomes matter. Retrospective patient data, longitudinal disease pathways, tissue organisation, treatment histories, and clinical endpoints encode causal information that no isolated assay can capture alone.

Understanding cancer and designing therapies should not proceed from isolated mechanisms in isolation. It should integrate retrospective patient trajectories, tissue level organisation, clinical trial outcomes, and molecular interventions, not as parallel silos but as components of a single causal system.

Toward a new view

Images alone are not enough. Mutations alone are not enough. Multimodality alone is not enough.

Cancer is neither a genetic bug nor a visual pattern. It is a failure mode of a complex, self organising system. The actionable path forward is clear. We must adopt causal, multi scale models as the foundation of AI in cancer biology. We must treat genes, cells, tissues, patients, and treatment pathways as interacting levels rather than hierarchical outputs. We must use AI not merely to predict or explain, but to test interventions and counterfactuals across scales. We must anchor discovery in real patient trajectories rather than isolated experimental abstractions.

AI should not be a pattern recogniser or a storyteller. It should be a tool for navigating strange loops.


Sunday, June 29, 2025

What Iqbal thinks of Artificial Intelligence?

 After giving it all of Iqbal's Urdu Poetry with English Translation, I asked ChatGPT to imagine itself as Iqbal and answer interview questions. Here is the response to my question about "What would Iqbal think of Artificial Intelligence?"


Artificial Intelligence? A marvel of human thought, no doubt—a flame sparked by the same fire that once taught Adam the names of all things.

But let me ask you:

Has man mastered himself before he dares to master machines?

Intellect (‘aql) is a lamp, but without ishq—love, vision, and spiritual yearning—it is blind.

If AI is born from intellect but lacks soul, then it is but a mirror reflecting our confusion, not our clarity.

I have seen the West bend mountains with science,

But has this knowledge birthed free men?

Artificial Intelligence may extend man’s reach—but will it deepen his insight?

It may predict his wants—but can it awaken his khudi?

Use it, yes. Shape it, yes.

But do not worship it, lest you forge new idols—cold, efficient, godless.

The greatest danger is not that machines will think like humans,

but that humans will forget how to think like men with soul.

Sunday, April 28, 2024

Can ChatGPT deduce the presence of anti-CRISPR proteins?

 

Can ChatGPT deduce the presence of anti-CRISPR proteins?



I asked ChatGPT to infer the presence of anti-CRISPR proteins by relying on its ability to reason. I gave it two separate prompts. In Prompt-1 I asked it to check if the known deduction of the presence of anti-CRISPR proteins is correct or not. In Prompt-2, I just asked it to infer a logically sound deduction from given information. 

I will let you judge the answers.


Prompt-1:

You are a master logician. I will give you some examples of logically sound and unsound deductive reasonings. Then I will ask you a question for you to check if that deduction is logical or not and also help validate the deduction as well as identify and report relevant sources on the internet to generate your answer:


Logically Sound Deductive Reasoning Examples:


All dogs have ears; golden retrievers are dogs, therefore they have ears.

All racing cars must go over 80MPH; the Dodge Charger is a racing car, therefore it can go over 80MPH.

Christmas is always Dec. 25th; today is Dec. 25th, therefore it’s Christmas.



Logically Unsound Deductive Reasoning Examples:


All zebras have stripes; tigers have stripes, therefore tigers are zebras.

Fourth of July always has fireworks; today there were fireworks, therefore it must be the Fourth of July.

Carrots are orange; oranges are orange, therefore oranges are carrots.


Question:


Bacteria use CRISPR to destroy viral DNA to prevent infections

Their CRISPR array is a record of DNA of previous infections

If a bacterial contains a CRISPR array that can target some part of the bacteria’s own DNA then that bacteria then such a bacteria should self-destruct as it will destroy its own DNA

However, such bacteria do exist 


Deduction: these bacteria must contain some mechanism of inhibiting CRISPR


Response to Prompt-1 from ChatGPT:

The deduction presented here relies on understanding the mechanism of CRISPR and its function in bacteria. Let’s analyze this step-by-step.


# Deductive Reasoning Analysis

1. **Premise 1**: Bacteria use CRISPR to destroy viral DNA to prevent infections.

   - This is scientifically accurate. CRISPR-Cas systems in bacteria serve as an adaptive immune system, where they use sequences saved in their CRISPR arrays to recognize and cut specific DNA sequences, typically from viruses.


2. **Premise 2**: Their CRISPR array is a record of DNA of previous infections.

   - True. The CRISPR array consists of snippets of DNA from viruses that have previously infected the bacterium. These snippets are used to recognize and defend against future attacks by similar viruses.


3. **Premise 3**: If a bacterial cell contains a CRISPR array that can target some part of the bacteria’s own DNA, then that bacteria should self-destruct as it will destroy its own DNA.

   - Logically, if CRISPR were to target the bacterium’s own DNA, it could lead to lethal consequences for the bacterium by damaging essential genes.


4. **Observation**: However, such bacteria do exist.

   - This indicates that there are exceptions where bacteria do not self-destruct despite having CRISPR systems that could potentially target their own DNA.


5. **Deduction**: These bacteria must contain some mechanism of inhibiting CRISPR.

   - This deduction logically follows from the observation and premises. Since the bacteria that could potentially target their own DNA do not always self-destruct, it is reasonable to infer that they have mechanisms to inhibit CRISPR activity under certain conditions to prevent self-destruction.


# Validation and Sources


Research in the field of CRISPR and microbial genetics has shown that bacteria have indeed evolved mechanisms to regulate CRISPR activity to prevent self-targeting. These mechanisms can include various forms of regulation at the genetic and molecular levels to ensure that CRISPR systems do not accidentally target the bacterium’s own DNA.


For example, some bacteria have anti-CRISPR proteins that inhibit CRISPR-Cas systems, and there are specific regulatory processes that help avoid targeting the bacterium’s own DNA unless certain conditions are met. These adaptations are essential for the survival of bacteria with CRISPR systems.


Prompt-2

You are a master logician. I will give you some examples of logically sound and unsound deductive reasonings. Then I will ask you a question for you to generate a logical deduction for it and validate your response with relevant sources from the internet:


Logically Sound Deductive Reasoning Examples:


All dogs have ears; golden retrievers are dogs, therefore they have ears.

All racing cars must go over 80MPH; the Dodge Charger is a racing car, therefore it can go over 80MPH.

Christmas is always Dec. 25th; today is Dec. 25th, therefore it’s Christmas.



Logically Unsound Deductive Reasoning Examples:


All zebras have stripes; tigers have stripes, therefore tigers are zebras.

Fourth of July always has fireworks; today there were fireworks, therefore it must be the Fourth of July.

Carrots are orange; oranges are orange, therefore oranges are carrots.


Question:

Bacteria use CRISPR to destroy viral DNA to prevent infections

Their CRISPR array is a record of DNA of previous infections

If a bacterial contains a CRISPR array that can target some part of the bacteria’s own DNA then that bacteria then such a bacteria should self-destruct as it will destroy its own DNA

However, such bacteria do exist 

Deduction: To be produced by you


Response to Prompt-2 from ChatGPT: 

The logical deduction from your question can be approached by carefully analyzing the statements and their implications:


Premise 1: Bacteria use CRISPR to destroy viral DNA to prevent infections.

Premise 2: Their CRISPR array is a record of DNA from previous infections.

Premise 3: If a bacterium contains a CRISPR array that can target some part of the bacterium’s own DNA, then such a bacterium should self-destruct as it will destroy its own DNA.

Observation: However, such bacteria do exist.


Deductive Reasoning:

Conclusion: Therefore, either the CRISPR system in these bacteria must have a regulatory mechanism that prevents self-destruction when targeting its own DNA, or the bacteria have adapted in such a way that CRISPR does not initiate an auto-destructive process even when its own DNA is targeted.


Explanation:

This conclusion accounts for the coexistence of bacteria with CRISPR arrays that can target their own DNA without leading to their self-destruction, suggesting a complex interplay of genetic regulation and evolutionary adaptations that prevent the scenario described in Premise 3 from occurring universally.


Validating the Conclusion:

Now, let's validate this deduction using relevant sources from the internet to ensure that it aligns with current scientific understanding. I will search for information regarding the regulation of CRISPR systems in bacteria and mechanisms they have to avoid auto-destruction when targeting their own DNA.


The logical deduction concerning the survival of bacteria that possess CRISPR arrays capable of targeting their own DNA can be strengthened by understanding the sophisticated mechanisms bacteria use to avoid self-destruction. The key to this prevention lies in the presence of protospacer adjacent motifs (PAMs). PAMs are short DNA sequences found adjacent to the target DNA sequences in viruses (protospacers) but not in the bacterial CRISPR arrays themselves. This distinction allows the CRISPR-Cas system to differentiate between foreign DNA (which contains PAMs) and the bacterium's own DNA (which lacks PAMs). Therefore, the Cas proteins only cut DNA at sites where a PAM is present, thereby safeguarding the bacterial genome from being targeted by its own CRISPR system.


Further insight reveals that the CRISPR-Cas system employs a detailed process to ensure specificity in targeting. Initially, the system transcribes the CRISPR array into RNA, which is then processed into crRNAs. These crRNAs guide Cas proteins to target and cleave DNA that matches their sequence, but only if a PAM is present, confirming it as foreign. This sophisticated safeguard is pivotal in preventing the CRISPR system from inadvertently destroying the bacterium's own DNA, which would be catastrophic for the cell.


In summary, bacteria have evolved a highly effective CRISPR-Cas immune mechanism that includes built-in checks such as PAM recognition to ensure only foreign DNA is targeted, thus allowing them to possess CRISPR arrays that could potentially match their own DNA without resulting in self-destruction​ (Innovative Genomics Institute (IGI))​​ (Frontiers)​​ (Microbiology Note – Online Biology Notes)​.




Sunday, July 16, 2023

On Love by Fayyaz Minhas (A translation)

--

It was before the nights of this world had received their darkness. Before even the stars knew how to twinkle. The newly formed moon stumbled awkwardly in its brightly lit dress. It was not even familiar with its duty of revolving around the Earth. The world had just emerged from the house of possibilities and was void of any life as we know it. Thus it was the very beginning of this system called the cosmos. Time itself had just been morphed.

There was an alchemist in the heavens at that time who could see the future of the world. He knew that God was in possession of a cure for everything but the angels were hiding the miracle from Adam. He set himself to get hold of the miracle cure and one day he did get hold of it. 

He then started collecting the ingridents required for producing it. He got brilliance from the stars, asked the moon for its grief (of separating from the Earth). Got darkness from the night. He acquired yearning from lightning, piety from a hooriah and Passion from Jesus, son of Mary. He collected Care-freeness from God Himself and Humility from angels.

He then mixed all these ingridents with the water of life And named the final product "love!"

He spread this substance over in whole of the universe And it is love that taught stars to move, flowers to blosson and life to thrive!

--

My humble translation of Iqbal's poem "Muhabbat" (Love) in Bang-e-Dara.

 http://www.youtube.com/watch?v=ATvGVLMdcC0



 جہاں کے جوہر مضمر کا گويا امتحاں تو ہے! 


The secrets of this world cannot hide from your eyes (Iqbal)

 "Don't Ask!" by Fayyaz Minhas

--

When my gaze questions her presence on my doorstep 

this late at night 

She gives me goosebumps as answers 

What's so special about her presence? 

Don't ask! 

When I dance with her, 

My quadriplegic soul

Never misses a beat or a step

What happens to my soul around her? 

Don't ask!

Sometimes I rise heartwards to meet her

Like a rose bush trying to escape it's muddy roots

Or a cloud flying high away from its watery origin 

Or the moon, running breathless without any air

Or the smoke taking to the skies, away from its fire

Who am I? Who is she? 

Earth? Water? Fire? Air? 

Don't ask!

Friday, June 9, 2023

Peeping Tom by Fayyaz Minhas (written May 16, 2021)

لیڈی گوڈئوا Lady Godiva آج سے قریب ایک ہزار برس پہلے یہاں سے گزری جہاں آج اس کا ایک مجسمہ اس کی برہنگی کی دلیل اور اس کی ہمت کی شہادت کے طور موجود ہے- تو بات کچھ یوں ہے کے والی شہر نے غریب کسانوں اور ان کے مال سے تجارتی نفع کمانے والوں پر آج کے حکمرانوں کی طرح ٹیکس لگایا- غیر کی کھیتی اور اس میں اگنے والی جنس پر نظر ہی تو سلطان' پرویز اور مجلس ملت کے رکن ہونے کی شرط ہے - زمانہ ضرور بدلہ ہو گا لیکن حاکم کی حاکمیت اسی طرح غربت اور کمزوری سے طاقت حاصل کرتی آئی ہے - ٹیکس اور اس سے پستی عوام کی حالت نے لیڈی گوڈئوا کے دل پر گہرا اثر کیا اور ایک شاہی خاندان کی چشم و چراغ ہونے سے پیدا ہونے والی ہمت نے انہیں حاکم وقت' جو کچھ روایات کے مطابق انکے شوہر نامدار بھی تھے' کے سامنے کلمہ حق ادا کرنے پر مجبور کیا- انہوں نے حاکم سے یہ سفارش کی کہ اس ٹیکس سے غربت کی چکی کی رفتار تیزہونے' اور اس کے پاٹوں کے بیچ عوام کے کچلے جانے کا قوی امکان ہے لہٰذا اس لگان سے معافی دے کر ثواب دارین حاصل کیا جاۓ - لیکن جہاں ایک جانب ثواب کی لذت اور دوسری جانب سونے کی چمک ہو' غلط فیصلہ کرنا بہت سہل ہوتا ہے - چنانچہ حاکم نے لیڈی گوڈئوا کی اس معصومانہ فرمائش کو نظرانداز کرنے کے بعد یہ کہا کہ اے مورکھ! تجھے نظام حکومت کا کیا علم؟ تو کیا جانے کہ غریب کے پسینے کی منی ہی تو امیر کی نسل کی افزائش کا سبب ہے - یہ لباس فاخرہ جو تیرے بدن کی زینت ہے ' اسی آمدن سے بنا گیا ہے - لگان کی معافی تو تب ہی ممکن ہے جب تم خود اس لباس سے اپنے آپ کو بری کرنے کیلئے تیار ہو - حاکم نے شائد یہ بات گوڈئوا کو سمجھانے  اور اسے اس ضد سے دور رکھنے کیلئے کی ہو لیکن گوڈئوا تو اس کو سچ سمجھ' کپڑے اتار' شہر کو نکل گئی کہ شائد حاکم اپنی زبان کا پاس رکھنے کیلئے ٹیکس معاف کر دے! کہتے ہیں کے ہر انسان کی زندگی میں ایک وقت آتا ہے جب حضرت خضر اسے سیدھا راستہ دکھاتے ہیں لیکن اس پر چلنا مشکل ہوتا ہے - اس راستے میں سب کچھ چھن جانے کے ڈر پر قابو پانا ہی ایک ولی کو ایک لالچی والی سے منفرد کرتا ہے - تو لیڈی گوڈئوا نے ایک پاک بی بی کی سنت کے مطابق حاکم وقت کے سامنے سچ بول کر اور اپنا سب کچھ چھوڑ کر اس راستے کا انتخاب کیا - وہ اپنے آپ کو اپنی زلفوں کی درازی میں چھپا کر محل سے نکل گئی - زلفیں جتنی بھی لمبی ہوں' شب دیجور میں تو شائد' لیکن دن کی میں روشنی میں لوگوں کی نظروں سے سب کچھ چھپانے سے قاصر ہی رہتی ہیں- لیکن شہر کے لوگ غریب سہی ' بے وضح نہ تھے - ان کو جب یہ معلوم ہوا کہ لیڈی گوڈئوا کی یہ حالت غریب کی داد رسی کی وجہ سےہوئی تو انہوں نے باہم عہد کیا کہ سب اپنے آپ کو گھروں میں بند کر لیں کہ کہیں لیڈی گوڈئوا کے برہنہ بدن پر انکی نظر نہ پڑے - ویسے بھی کہتے ہیں کے ایسی نوری مخلوق ہم زمینی باسیوں کو کہاں نظر آتی ہیں؟ لیکن انسان کی جبلت میں جس چیز سے منح کیا جاۓ وہ کام کرنے کی خواہش جنت گم گشتہ سے موجود ہے - اس کہانی میں بھی ایک برہنہ عورت کے وجود نے ایک کم ظرف بہ مسمم ٹام کو آبلے پھاڑ  کر لیڈی گوڈئوا  کی برہنگی سے لذت حاصل کرنے پر مجبور کر دیا - ٹام کی اس حرکت نے انگریزی زبان کے محاورے peeping tom کی بنیاد رکھی - خیر روایت یہ ہے کے ٹام کو اس گناہ کی سبب قہر خدا نے اندھا کر دیا اور آج شہر کے مرکز میں موجود یہ مجسمہ تو لیڈی گوڈئوا کیلئے ہے لیکن اس مجسمے سے کچھ دور ایک کھڑکی میں اندھا ٹام بھی اسی حالت گناہ میں بیٹھا ہے - مجھے نہیں معلوم کے اس واقعے سے  متاثر حاکم نے کیا واقعی ٹیکس معاف کیا یا نہیں ' یا شہر کے لوگوں کی غیرت نے خاموشی کی چادر سے نکل کر رسم شبیری ادا کی یا نہیں' لیکن زینب کی بے چادری کی مانند یہ قصہ بھی تاریخ کا حصّہ ہے  

آج میں نے دیکھا کہ لیڈی گوڈئوا کے مجسمے کے ساۓ میں کچھ لوگ جمح ہیں - ایک مظاہرہ جاری ہے جس کے منتظمین حمایتان حریت فلسطین ہیں - وہاں ہونے والی تقریر کا مجھے ایک لفظ سمجھ نہیں آیا- اسکی وجہ شاید یہ تھی کہ میں  peeping tom کی طرح مظاہرے میں شامل لوگوں اور انکو دیکھنے میں مگن لوگوں کو دیکھنے میں مصروف تھا جو برطانوی موسم گرما سے کئے وعدہ بے حجابی کو پورا کر رہے تھے- ارد گرد نظر دوڑائی تو لوگ قریب واقع دکانوں ' شراب خانوں اور رستورانوں میں زیادہ بے فکر دکھائی دیے - پھر جی میں یہ خیال اٹھا کہ شائد بے سروسامان اپنے گھروں سے نکلنے کو شائد یا فلسطینی سمجھ سکتے ہیں یا سنائی کے موسوی یا لیڈی گوڈئوا کا مجسمہ! وہاں کچھ اسرائیلی پرچم بردار بھی تھے اور فلسطینی بھی! اور میری نگاہیں ایک گندمی بالوں والی خوبصورت پولیس افسر پر مرکوز تھیں جس سے میرے خیالوں کے امن میں تھوڑا خلل برپا ہوا لیکن اس کا اصل مقصد اس نازک صورت حال کو قابو میں رکھنا تھا جو ان سیاسی خیالات اور اس تاریخی تقسیم کے حامیوں کے ایک جگہ اکھٹے ہونے سے بگڑ سکتی تھی- خیر نہ کچھ ہونا تھا نہ کچھ ہوا - لیکن میرے ذہن میں آج سے ایک ہزار برس بعد کا منظر ابھرا جس میں  لیڈی گوڈئوا کے مجسمے کے ساتھ ایک طرف جھلستی Anne Frank  اور دوسری طرف بمبار حملوں میں مرنے والے بے نام فلسطینی بچے کا مجسمہ تھا اور میں تمام دنیا کی مانند اپنی کھڑکی سے اندھا ٹام بن کر یہ سب دیکھ رہا تھا- شائد اس سب کے بعد ہم سب انسانیت کا لباس پہننا سیکھ لیں

Friday, February 24, 2023

Dance

  نی جندے نچ نی جندے نچ نی جندے

 نچ نی جندے نچ نی جندے نچ نی جندے


جد تک سیت وجودے تیرے ہے ساہواں دا مچ


نچ نی جندے نچ نی جندے نچ نی جندے نچ


نچ نی جندے نچ نی جندے نچ نی جندے نچ


می رقصم می رقصم بولا ہر دم مونہوں بول


ایسی اڈی مار زمینے مڑھکے تھاں رت ڈؤل


پانی مٹی اگ ہوا نوں اک پیالے گھول


اکو ڈیکے پی جا چارے پنجواں کھلے سچ


نچ نی جندے نچ نی جندے نچ نی جندے نچ




دس نی جندے دنیا نوں توں ایہہ انملا کم


کیوں سولی منصور نے چمی شمس لتھیا چم 


کیوں موہرا سقراط نے پیتا کیوں سی نچیا بلھا


کیوں سی بھلی ہیر سلیٹی ویہڑا چوکا چُلہا


سچا تیرا سچ پچھانے کیہہ جانے جو کھچ


نچ نی جندے نچ نی جندے نچ نی جندے نچ




دس نی جندے کہیڑی گلوں سرمد سیس کٹایا


تخت ہزارہ چھڈ رانجھے نیں کناں نوں پڑوایا


شاہ حسین دا کیہڑی گلوں بنیا مادھو لال


چھڈ دولتاں ادھم کاس نوں ہویا سی کنگال


عشقے دی سردائی پی کے بول فقیرا سچ


نچ نی جندے نچ نی جندے نچ نی جندے نچ




روز الست و کیتے سن جو کھلن قول قرار


لالچ ، لوبھاں ،حرص، ہواواں اپنے اندروں مار


میں میں توں کر لے توبہ توں توں ورد پکار


توں دے ایس سمندر دے وچ قطرہ بن کے رچ


نچ نی جندے نچ نی جندے نچ نی جندے نچ




ایس مقامے مرنوں پہلاں مر جاناں توں آپے


جمیاں دے سب چاء مک جانے موئیاں یار سیاپے


آپے آؤنا آپے جانا کھل جانی ایہہ گل


کت کت ڈھیر لگا دؤو تکلا نکل گیا جے ول


لاہ ناں پردے یار ندیما اس دنیا توں بچ


نچ نی جندے نچ نی جندے نچ نی جندے نچ




غلام حسین ندیم



Wednesday, September 4, 2019

ہک گل پچھاں

ہک گل پچھاں' مارو گے تے نہیں؟
ایہہ تساں مارنا کس سکھایا جے؟ 

میرے دیس دے واسیوں! ہک گل پچھاں؟
"و بالمساکین إحسانا" کتھے جا بُھلایا جے؟

میرے دیس دے سپاہیوں! ہک گل پچھاں؟
تہاڈے ظلم دا پرچہ اس کتھے جا کٹایا جے؟

میرے دیس دے منصفوں! ہک گل پچھاں؟
تساں تَحْكُمُوا بِالْعَدْلِ کتھے جا پھیلایا جے؟

میری سرکار دے افسروں! ہک گل پچھاں؟
اپنڑی گردن اِڈا سریا کتھے جا پوایا جے؟

میرے دیس دے سیاسیوں! ہک گل پچھاں؟
ملک الله' حکم الله کتھے جا دفنایا جے؟

میرے دیس دی مقدس گائیوں! ہک گل پچھاں؟
 ایہہ اپنڑے آپ نوں خدا کتھے جا بنایا جے؟

میرے دیس دے لکھاریوں! ہک گل پچھاں؟
میری جِب وانگوں سچ کتھے جا دکھایا جے؟

میرے حسین دے ذاکروں! ہک گل پچھاں؟
اِس غریب دا ماتم  کتھے جا کرایا جے؟

(فیاض)

Sunday, April 14, 2019

Books are people too (ep. 4): Payam-e-Mashriq


This is another interview in the series "Books are people too!". This time, our guest is Huzoor Ahmed Saleem's Urdu translation of the Persian poetry book "Payam-e-Mashriq" (Message of the East) by Iqbal.


Who should I take as a guide in my life?

شعاع مہر او قلزم شگاف است
بہ ماہی دیدہ رہ ایں دہد عشق

شعاع مہر ہے دریا میں گویا
کہ ماہی  کو ہے چشم رہ بیں عشق

What is the role of mankind in this universe?

ہے ساز نغمہ ہائے عشق انساں
کرے افشاۓ راز اور خود ہے پنہاں
بنے وہ جہاں کو ' یہ سنوارے
ہے انساں کیا شریک کار یزداں؟

How can I improve my life?

دمادم نقش ہاے تازہ ریزد
بیک صورت  قرار زندگی نیست
اگر امروز تو تصویر دوش است
بخاک تو شرار زندگی نیست

بناتی ہے بہر لحظہ نۓ نقش
نہیں دائم قرار زندگانی
ہے تیرا آج اگر تصویر کل کی
نہیں تجھ میں شرار زندگانی

What is the objective of life?

مگو از مدعاۓ زندگانی
ترا بر شیوہ ہاۓ او نگہ نیست
من از ذوق سفر آں گونہ مستم
کہ منزل پیش من جز سنگ رہ نیست

بیاں کرتا ہے کیا تو مقصد زیست
نظر ایسی نہیں ہے تجھ تو حاصل
ہوں میں سرشار یوں ذوق سفر سے
کہ سنگ رہگزر ہے مجھ کو منزل

Aren't we bounded by fate?


نہ ہو پا بستہء زنجیر تقدیر
ہے جولاں گاہ زیرِ چرخِ گرداں
نہ آۓ گر یقیں تو کر کے ہمت
جھٹک زنجیر پا' پھر دیکھ میداں

How can we humans live in peace?

نہ افغانیم و نے ترک و تتاریم
چمن زادیم و از یک شا خساریم
تمیز تانگ و بو بر ما حرام است
کہ م پروردہ یک نو بہاریم

نہ افغاں ہیں ' نہ ہم ہیں ترک و تاتار
سبھی نکلے ہیں اک شاخ چمن سے
تمیز رنگ و بو ہم کو ہیں ممنوع
کہ پروردہ ہیں سب اک فصل گل کے

Why were we born?

ازل کی وسعتوں میں پرفشاں تھا
نہ تھا پابند میں اب اور گل کا
گراں قیمت ہوں میں تیری نظر میں
تبھی بازار ہستی میں تو لایا

Who are you?


If the world was created by Him, what did humans add?



Sometimes, life feels difficult. How does one deal with that?


پوچھا یہ ایک دن ایک صاحب دل سے' ہے کیا حیات؟
جتنی شراب تلخ ہو بہتر" دیا جواب"

What inspires you to explore the world and knowledge?
جو ملک بھی ہے میرے خدا کا' وہ ہے مرا 
ہر ملک ملک ماست کہ ملک خداۓ ماست

What is the worse thing a human can do to himself?

اپنی کج بینی سے آدم ہوا آدم کا غلام 
اپنے جوہر کو کیا اس نے نثار کے و جم 
گھٹ گیا کتے سے بھی خوۓ غلامی کے سبب 
سامنے کتے کے کتے نے کیا کب سر خم





Tuesday, February 19, 2019

Saving yourself from grief over loss of computation

Original post: Original post link


You are running a long simulation of about 30 days and the power fails on the 29th day (or something equally tragic happens!). How would you react? Enter the classic case of 5 stages of grief: Denial (Nooooo!!!!), Anger (*&(#^&*(#@%&!!!!), Bargaining (It must’ve produced some output!), Depression (I’m never gonna graduate!) and Acceptance (Well, let’s restart the simulation!).
But before you restart your simulation, hear me out!
I have had this issue many times and had been thinking about how to avoid this. Here are some of the solutions I came across:
  1. UPS: An Un-interrupted Power Supply can potentially save you from this… But how can I stop my simulation midway if the power is not back up before the UPS dies out?
  2. NVDIMM: This is another hardware solution which uses Non-volatile RAM (NVDIMM) which copies your RAM in a non-volatile memory and then restores it when the power comes back online. It is a developing technology but can be very useful. Read more about this here. However, if you don’t have deep pockets, this is, at this time, a volatile option!
  3. Manual checkpointing: Checkpointing is the art of saving a snapshot of the state of your software or simulation onto a hard-disk and then restoring it when you need to! You can do this easily if you are writing your own code: save all important variables into a file every so many minutes and then restore them from the file. However, manual checkpointing can be a pain so I began looking for automatic checkpointing aka Checkpoint-Restore solutions! An ideal (albeit extreme) scenario would be to be able to save the whole Operating System state and restore it as if nothing happened. Below are a few solutions towards that.
  4. Hypervisors: If you can tolerate the performance loss and other issues associated with using a virtual machine (virtual-box, VMware, etc.), you can use the hypervisor’s “snapshot” mechanisms to store and then restore the state of your system. Read more about this here.
  5. Docker: Docker is essentially a native hypervisor, i.e., it does not have the overhead of a virtual machine because the processes do not run in a guest operating system but in the host OS from within docker. Docker is excellent — for installation, distribution and also for checkpointing. The idea here is to make a docker box of your simulation software and then use the underlying checkpoint and restore technology to restore the software after a failure. Read more about this here. However, this entails a significant additional overhead in making the docker container.
  6. CRIU: CRIU (pron. Kree-oo) stands for Checkpoint and Restore in User Space. With CRIU “you can freeze a running application (or part of it) and checkpoint it as a collection of files on disk. You can then use the files to restore the application and run it exactly as it was during the time of the freeze. With this feature, application live migration, snapshots, remote debugging, and many other things are possible.” Here is a complete list of usage scenarios. CRIU supports checkcpointing with docker as well. This is my second favorite tool for this purpose!
  7. DMTCP: This is my favorite solution — it allows you to create checkpoints and restore them in a very easy manner. It comes with Linux (or you can sudo apt-get install dmtcp). However, I would recommend the following process to install it: Download the DMTCP package in your Linux distribution as a .zip file and then extract it to a folder of your choice. After that go into the folder and execute “./configure” and “./make install” and that’s it! After installation you are ready to use it: For a demo, go to the contrib/python folder within your dmtcp folder with your terminal and execute “dmtcp_launch python hookexample.py” to start an example process. This will create a dmtcp checkpoint as well as a script that allows you to restore the process as and when required using ./dmtcp_restart_script.sh. This video also explains the process in more detail. These checkpoints also allow for great debugging by saving the state of your software.
8. Ruffus
Ruffus is a library for python that allows you to setup and execute a computational pipeline composed of multiple steps in which the output of one step becomes the input of the next. It also supports pretty easy checkpointing.
9. EdiblePickle
EdiblePickle also allows checpointing. Here is a simple example.
import string
import time
from ediblepickle import checkpoint

# A checkpointed expensive function
@checkpoint(key=string.Template('m{0}_n{1}_${iterations}_$stride.csv'), work_dir='/tmp/intermediate_results', refresh=True)
def expensive_computation(m, n, iterations=4, stride=1):
    for i in range(iterations):
        time.sleep(1)
    return range(m, n, stride)

# First call, evaluates the function and saves the results
begin = time.time()
expensive_computation(-100, 200, iterations=4, stride=2)
time_taken = time.time() - begin

print time_taken

# Second call, since the checkpoint exists, the result is loaded from that file and returned.
begin = time.time()
expensive_computation(-100, 200, iterations=4, stride=2)
time_taken = time.time() - begin

print time_taken

Follow it here: https://medium.com/@fayyazafsar/saving-yourself-from-grief-over-loss-of-computation-688819d85389

Sunday, January 20, 2019

Books are people Too (Ep. 3): Advice to a young scientist by P.B. Medawar

In the third episode of our "Books are people too" interview series, we have, as our guest, an extremely useful book for our young scientists and researchers. The name of the book is: "Advice to a young scientist". It was written by Sir Peter Medawar, a British scientist, who is regarded as the father of transplantation because of his work on organ and tissue transplants. Dr. Medawar was awarded a Nobel prize in 1960 for his ground-breaking work in the field. Advice to a young scientist (AYS) was written in 1979 and it has aged extremely gracefully to almost a wise sage or an oracle one should consult every so often.


FM: Welcome to our interview series. If you ask a kid to tell you what a scientist his, he or she would immediately respond with someone in a white coat blowing away stuff. Is that what you think as well?

AYS: Haha, not just a kid but most people in the society would associate a similar image with a scientist in their mind. However, I feel that we must always realize that scientists are people too! They are affected by the same nobilities and vices as any one else. The term "scientist" was coined in 1844 to describe someone who works in science.

FM: And how would you define science?

AYS: To me, science is nothing more than an exploratory activity whose purpose is to come to a better understanding of the natural world. And this activity is called research! However, there are other science based or scientific activites in addition to research as well such as scientific administration, scientific journalism, teaching science, scientific advisory, supervision, industrial process management,  etc.

FM: So, according to you, anyone engaged in research is a scientist, No?

AYS: Yes! And we must never forget that there may be many practitioners of science and the scientific method who may not be officially labeled as scientists but are doing good quality science, for example, a pool cleaner who checks the hydrogen ion concentration of the water, keeps an eye on the bacterial and fungal flora and studies their effects on humans!

FM: So instead of asking what qualifies for good science, let me ask you what makes a "bad" scientist?

AYS: It is pretty simple, just like any other profession, if you are into science for the wrong reasons you will be terrible at it!

FM: What is or are the right reason(s) to get into science: curiosity, love of details, finicking?

AYS: Ummm... I think it is more than that. Good scientists I have seen have a sort of an exploratory impulsion or a restless endeavor to get to the truth of things! They feel uneasy if they can't understand or explain something they see and can't stop themselves getting to the heart of it!

FM: How can one find out if one is made to be a scientist?

AYS: I think the existence of inbuilt tendencies to be a scientist are over-glorified! Don't get me wrong -- they are important but skills required for science can be and must be learned as well. If someone thinks that their thinking can make them a good scientist without learning the skills required for doing science and experiments, they are, in my opinion, not made for science. Manual work such as doing experiments or, more directly, programming in your case should never be considered "below" science as these also help you think and be a better scientist! If someone thinks that being a scientist entails having lesser mortals such as graduate students fulfill his or her whims, they wouldn't typically make good scientists. The novice who tries his hand at research and finds himself indifferent to or bored by it should leave science without any sense of self-reproach or misdirection.

FM: So how can a young scientist pick a field or research topic?

AYS: It is pretty simple to say but maybe a little difficult to follow: if you want to make important discoveries, you must study important problems. Dull or piffling problems yield dull or piffling answers. By important problems, I mean to refer to problems whose answers would matter even if your work is not necessarily fashionable or sexy. It is perfectly okay to fall in line with a larger field of research, for example, molecular genetics or cellular immunology or machine learning but it is not advisable to fall in with a prevailing fashion for a new histochemical procedure or a new classification approach and just stick to it!

FM: What is your opinion about Ph.D. programs?

AYS: Human life can continue without a Ph.D. However, a Ph.D. is a license or passport for immigrating into any academic institution and it does have its merits. But it is important for a student to think why one wants to go for a Ph.D., what they want to work on, who they want their mentor to be and what would he do after a Ph.D. One of the major consequences of modern Ph.D. programs is that once one gets into a Ph.D. program, one is then expected to continue in a scientific or academic career because one doesn't know anything else to do! Therefore, it is imperative to really think hard before committing to such a career choice. After a Ph.D., a scientist must not continue working in the same direction for the rest of his life and should be willing to explore different things before settling on something they truly like.

FM: And about post-doctoral research?

AYS: Oh yeah! I feel that post-doctoral research is very important as it gives a budding scientist a chance to work on something they want to do, possibly in a different or related field, after having gone through their doctorate degree. As a consequence, post-docs are typically more motivated and make better researchers.

FM: Better than a thousand days of diligent study is one day with a great teacher. How can a scientist pick a mentor or a Ph.D. advisor?

AYS: The easiest, and not necessarily recommended, way is to pick the closest person at hand: the head or senior faculty in the department from which you graduated who may be looking for a disciple or an extra pair of hands. However, if a student understands or is proud of the work being done in the department then it is perfectly okay to do so but after much deliberation. The best way these days is to simply explore different scientists working in the field that a student likes and try to work with them! Don't just work somewhere without aligning your chosen field of research with what goes on there!

FM: How much should a scientist read to be successful?

AYS: I feel that most young scientists give too much emphasis on equipping oneself. They focus too much on reading the latest work and trying to know each and every new technique that is published to satisfy their sense of "being equipped to do great research". However, there is practically no limit to it. Too much reading also has psychological consequences and can be a hurdle to conducting actual or original research. It is like reading romantic novels all the time instead of trying to actually trying to talk to the girl sitting next to you! By far the best way to become proficient in research is to get on with it -- pick an important problem and work passionately in the pursuit of finding answers to it. I recommend to NOT learn new skills or mastering new disciplines until the pressure is upon to do so in this pursuit of finding answers; thereupon they can be mastered pretty quickly as there is plenty of motivation at hand. However, I must also say that reconstructing someone else's work or understanding a paper is important for two reasons: it helps you identify new and interesting problems or short-comings and it gives you confidence. Do it but don't over-do it!

FM: You refer to the art of research as "art of the soluble". What does that mean?

AYS: The art of research is that of making a problem "soluble" by finding out ways of getting at it -- how to easily attack a problem. One easy way I have found of attacking tough problems is to begin by quantifying things related to the problem such as how strong is the reaction of a patient to a transplanted tissue? Or, in your case of working on neural networks, how important is a particular neuron in a neural network? Typically, if you can quantify an effect you can make the problem soluble.

(to be cont'd)

Sunday, January 13, 2019

Interviews with books Ep. 2: Humzad da Dukh by Tariq Aziz

Books are people too: Interviews with books


Welcome to the second episode of interviews with books with Fayyaz. The objective of this series is to interview a book as a person after reading it. In this episode, we shall interview "Humzad da dukh" by Tariq Aziz. It is a punjabi poetry book written and is one of my favorites. The interview will be in Punjabi.



ایہہ تہاڈے ہمزاد دا دکھ ہے کی ؟



آپنے دکھی ہمزاد توں علاوہ تے تسی مینوں بہوں کلے لگے او' ایس دی کی وجہ اے ؟


کسی دے نہ ملن دی کی وجہ بنی ؟


کوئی تے اچھا لگیا ہوۓ گا، اوھدی کوئی نشانی تے دسو ؟


اوس فرزانہ دی یاد آندی اے تے کی کردے او؟ کوئی دعا؟


ہک دوجے توں دور' ہویا کی سی ؟


اوس دے نال گزری کوئی خاص یاد؟


خیر' تہانوں سب توں زیادہ پیار کس کولوں ملیا؟


تسی اپنے ملک دے بارے اچ کی سوچدے او؟


اپنے دیس لئی کی خواہش اے؟



بچے وی تہاڈی گلاں سندے پیۓ نے' انہاں دے واسطے کوئی پیغام؟



تے وڈیاں لئ؟



آپنے تے میرے واسطے کوئی خواہش یا دعا؟





Saturday, January 12, 2019

Book interviews: Thinking like a freak

Books are people too: Interviews with books

"Thinking like a freak!" by Levitt and Dubner





The objective of this series is to interview a book as a person after reading it. In this episode, we shall interview "Think Like a Freak" by Levitt and Dubner who had previously authored the famous "Freakonomics" and "Superfreakonomics" books. The book starts off with "The authors of Freakonomics" offer to retrain your brain" right on the front cover. So we start off with this as a question.

Interviewer (Fayyaz Minhas, FM): Thank you for your time for this interview. Let me get straight to the point. What does it mean to think like a freak?

(Think Like a Freak, TLAF): Thank you for the opportunity for the interview. However, I had anticipated this question and have a well-prepared answer for this. I would first like to emphasize the fact that very few people think or, in the words of George Bernard Shaw "Few people think more than two or three times a year!". My catchy name is to encourage people to think first and then as a freak. Its simply to encourage people to take a break from their screens and sit in a corner and do nothing but happily think! Now about thinking like a freak --- In my opinion, a freak is someone who is an eccentric, an original thinker, who goes in depth of the obvious and the not-so-obvious in his analysis. Such a person, like children, is not afraid of being judged at asking "stupid" questions, challenging the status quo, thinking small instead of big, quitting, failing, or simply admitting "I don't know!".

FM: Great! So, how can we start thinking like one?

TLAF: By realizing that we don't know everything! As children, we don't have such mental biases that prevent us from asking simple questions but as we grow up, we stop taking the smiles people get at our questions as mere smiles and consider them as smirk criticism. This, and the mockery of school tests in which we are graded over not thinking but knowing, kill the little freak in us. We must keep that freaky child alive in all of us or give it a rebirth. We must also realize that we mostly think of ourselves to be better than we actually are. Remember how a large majority of people in a survey label themselves to be above average. It's easy to start thinking this way if we know we need improvement and are motivated to follow up on this! Also, instead of thinking Big all the time, think about small things or basic or fundamental things as it would lead you to big answers!

FM: How?

TLAF: I don't know what would work for each one of us in that regard but one of the ways that might be done is ask yourself "What is your problem?" and get to the root of the problem. As I said in the text, "Like a bad dye job, the truth is in the roots!". However, this may require a lot of digging around until you get what you want. It also requires you to know if you are asking the right question and if you really want to find the answer. My coin trick can work that you can use to judge if you really want something or not by tossing a coin and then knowing whether you would wish it were heads or tails!

FM: You keep saying that children are ideal thinkers, but the problems they have are pretty small in comparison to what we experience as adults. So how can we "scale up"?

TLAF: I mean to say that we can learn a lot from children but it requires us to let go of our thinking of ourseleves as smarter than children. Children typically get what they want and don't give up easy. This means there is something to learn from them. Kids don't buy into dogma and don't typically think about pleasing everyone around. They are curious otherwise who-without-a-freaky-mind would want to put their tiny pinky into an electric socket? Another great thing about kids is that they don't overthink. Ever seen a kid think about the futility of having to climb back onto a slide just to come down again?

FM: Okay, I get it. You have also talked about how to work with people. What tips would you like to give in this regard?

TLAF: The first thing we need to realize is that we can never be alone. Solitude is needed and mandatory for the survival of the soul and the inner freak. However, for the most part of our lives, we must interact with other people. The biggest idea I have come up with is that people like incentives, to feel in control (note that I didn't say that they like "being" in control), be appreciated and be productive. To work well with people you need to figure out what people really care about and this may be different from what they say they care about and then incentivize them on the aspects that are precious to them but easy for you to provide.

FM: How have been so successful?

TLAF: Haha, thanks for the compliment. It's easy if you keep you "weed out" unwanted stuff from both within you and around you to focus on what you like. As "The Subtle art of not giving a f*ck" says, there will always be problems, you just need to pick the ones you like and work with them! Also, once you accept an early failure and be happy about it, you can keep going on without hurting yourself too bad and it will ultimately lead you on to good times!

FM: You are pretty persuasive in your approach of writing and convincing people who may hold opposing views. There must be a strategy behind it, no?

TLAF: So I feel that it is easy to persuade someone if this is actually what you want to do. If you start calling names to people then, may be, you just wanted them to feel bad about themselves and not convince them. People tend to react more strongly to negative criticism than positive statements. In the human psyche, "Bad is larger than good". Also, having a disagreement with someone does not mean that what they are saying is wrong. One must acknowledge the valid points in their arguments. And the best of all: To convince people, try telling them stories instead of giving rules or anecdotes! Make the argument interesting to them!

FM: Cool! Actually, that is what inspired me to start this book interview series. I felt if I were to review this book it would be pretty dry and I may not be able to persuade a lot of people to read my boring reviews but this seems like a better approach and might work. I am also thinking of starting a story series for my teaching as well. So thank you for that idea. And thank you for your time as well.

TLAF: Thank you! Do read "Think like a freak!" again after a while but in the meanwhile and more importantly "Keep thinking like one!".

Sunday, November 11, 2018

Poem by Ehsan Akbar

اک منزل پچھلے چاند کی
نت روشن جس کی لو
وہ وقت کو پیچھے چھوڑ گئی
اسے دھنّے واد کہو
دابی ہوئی پور کماد کی
جو پھوٹی مگھر پوہ
کتنوں کو یہی اک چاہ تھی
وہ صرف مخاطب ہو
اے روپ جمال وصال کے
ترا کون سا ہے شبھ ناؤں
وہ جن میں تیرے لوگ تھے
کن گھاٹوں اترے گاؤں
کن صدیوں پر تری چھاؤنی
کن نسلوں پر تری چھاؤں
کہہ کتنی نرم دہائیاں
ترا دیکھتے گذریں روپ
کن پلکوں میں تری چھاؤں تھی
کن چہروں پر تری دھوپ
تری نظر نیازیں بانٹتی
بھکشا میں روپ سروپ
تو کس سرما کی چاندنی
گرما کی شکر دوپہر
تو صبح میں سویا بالکا
تو گاؤں میں پچھلا پہر
ست رنگا خواب فقیر کا
یا بھید بھری دوپہر
اک پوری نیند کی شانتی
تری کجلے والی لہر
اے سنبھلے جسم کی نازنیں
کئی عمریں تجھ پر تنگ
تو شبد قدیم کتاب سے
اظہار سے جس کی جنگ
تو ذات حیات کے ساتھ کی
کیوں نکلی غیر کے سنگ؟
تو سینوں بیچ پدھارتی
کیوں تو نے اوڑھے رنگ
میں شاعر پچھلے جنم کا
تو میری پرانی منگ
اب جیون اوڑھ کے آئی تو
سہہ تنہائی کے ڈھنگ