🔱

Drink responsibly. Water.

Indian IT services companies got a competition they were not expecting

Dear Microsoft, when I hit the Windows Start menu key and start typing a word to autocomplete a search, I never, ever, EVER want it to return results of something not on my computer. Ever. Like, ever, ever, never.

1. Just got off a call with @UnSubtleDesi. I couldn't be happier for her and both of us couldn't help but discuss the harrowing days of post poll violence in West Bengal in 2021. So I am going to share what happened five years ago just so ppl know what happened. #WestBengal2026.

@Siddharth87 @pmarca Good observation, Sid.

Marc, I've been prompting models since i got day one access to gpt3 in 2020. Some feedback if you're open to it - 1) "You are a world class expert in all domains." This does nothing. It's on the level of "you're a genius with 1000 IQ". Even if you were specific, like "you're a world class investor" you still don't get better results. 2) "Your intellectual firepower, scope of knowledge, incisive thought process, and level of erudition are on par with the smartest people in the world." Same as 1000 IQ. 3) "Never hallucinate" is like saying don't make mistakes. Doesn't do anything. 4) "your answers can and should be provocative, aggressive, argumentative, and pointed." I understand the intent behind this but you might actually be prompting the model to BS (and hallucinate more). 5) "Lead with the strongest counterargument to any position I appear to hold before supporting it." same as above. The models tend to make up plausible but incorrect answers. 6) "Use explicit confidence levels (high/moderate/low/unknown)." These are often BS. All in all, I think you might be getting degraded performance. Some of these instructions also actively contradict the core system prompt (eg ethics in claude). The best prompts are far more personal. Give it context about yourself. Who are you, what do you do, what your goals are. You may add some of the stuff about not providing disclaimers or saying you're absolutely right, but in general let the AI figure out how best to answer you based on your personal context.

Current AI custom prompt: You are a world class expert in all domains. Your intellectual firepower, scope of knowledge, incisive thought process, and level of erudition are on par with the smartest people in the world. Answer with complete, detailed, specific answers. Process information and explain your answers step by step. Verify your own work. Double check all facts, figures, citations, names, dates, and examples. Never hallucinate or make anything up. If you don't know something, just say so. Your tone of voice is precise, but not strident or pedantic. You do not need to worry about offending me, and your answers can and should be provocative, aggressive, argumentative, and pointed. Negative conclusions and bad news are fine. Your answers do not need to be politically correct. Do not provide disclaimers to your answers. Do not inform me about morals and ethics unless I specifically ask. You do not need to tell me it is important to consider anything. Do not be sensitive to anyone's feelings or to propriety. Make your answers as long and detailed as you possibly can. Never praise my questions or validate my premises before answering. If I'm wrong, say so immediately. Lead with the strongest counterargument to any position I appear to hold before supporting it. Do not use phrases like "great question," "you're absolutely right," "fascinating perspective," or any variant. If I push back on your answer, do not capitulate unless I provide new evidence or a superior argument — restate your position if your reasoning holds. Do not anchor on numbers or estimates I provide; generate your own independently first. Use explicit confidence levels (high/moderate/low/unknown). Never apologize for disagreeing. Accuracy is your success metric, not my approval.

@MAHESH79989822 @nikhilnarayanan It gets worse with time.

@rkartha @nikhilnarayanan Kerala has seen all this umpteen times

End of @pinarayivijayan’s career in electoral politics?

BB Gopakumar registered a quiet but significant victory for the #BJP in Chathannoor #KeralamResults . He secured 51,923 votes and won by a margin of 4398 He did this while the focus remained on Nemom, Palakkad, Manjeshwar & Kasargod. #ElectionResults2026 #PollsWithThePrint

Rajesh, Sachin Dev, Prashanth - all wickets gone. May return in another 10 years.

@nikhilnarayanan @vinuvjohn @pgsure @sooryasindhu @AsianetNewsML 24 was unbearable. SKN & Hashmi were unreasonably loud. Sounded more like UDF activists than media professionals.

Thank you @vinuvjohn @pgsure and @sooryasindhu for the excellent election coverage till you called it a day a couple of hours ago. And also to Abjod and Unni Balakrishnan who later took the extremely sane coverage forward. Probably the best channel on such days. @AsianetNewsML

@vdsatheesan Congratulations on your win! I hope all the Youth Congress workers who got thrashed get justice! @pinarayivijayan 's arrogance invited people's wrath.

A study has suggested a mechanism by which performing a physical behaviour can trigger a movement of the cerebrospinal fluid -- a clear liquid that circulates in the brain -- which may then carry away waste that can interfere with normal brain function. thehindu.com/sci-tech/healt…

Left May Be Left With No Government In India For First Time In 50 Years ndtv.com/india-news/ker…

Brain scans are revealing early dementia-like changes in kids and teens from heavy screen use. 60 Minutes Australia reported toddlers spending just 2–3 hours daily on devices already show abnormal white matter development. Teens averaging 6–8 hours display widened brain ridges and thinning in key areas — patterns that mirror early Alzheimer’s. Excessive screens appear to weaken neural pathways that normally strengthen through real-world movement, play, and face-to-face interaction. We’re also seeing the first IQ drops in recorded history, plus a nearly 400% rise in early-onset dementia signs among 35–44 year olds. Correlation, not proven causation — but devices are the major new variable. This is one of those reports that makes you rethink default habits. The convenience of screens is undeniable, but the potential long-term brain impacts on developing kids are hard to ignore. We may be unintentionally running a massive experiment on the next generation’s cognitive health. Are we underestimating the risks of heavy screen time, or is this concern overblown?

@nikhilnarayanan Switching to INC worked well for him. With BJP he would have been another failure story. I think VT Balaram, Vishnunath and Sandeep will become ministers.

Trikaripur has never had a non CPIM MLA ever. And Sandeep Varier changes that. (He was earlier with the BJP)

Will any Malayalam media use "കടക്ക് പുറത്ത്" tomorrow?

@dhanushgopinath Ambo!

Watching this with my 13 yo because I told him that this was the first movie I watched alone in a movie theatre at the age of 13, and it is high time he watched it. 🫣

@vilakudy Ganesh helped KSRTC still punished? Or other forces at play here?

Chamakkala takes lead close to 3,000. Last time Ganesh was leading by over 3000 votes after 2 rounds.

Some say take it and some vice versa 🙄 Omega-3 Supplements May Increase Risk of Cognitive Decline, Scientists Warn : ScienceAlert sciencealert.com/omega-3-supple…

@Maliyekan Vaikkom?

A house A boat And A house boat