Manish

[Manish @ManishSep1989]

@navikakumar @thevirdas @thevirdas she is not even worth the rant. Just ignore these people, they will fade away into oblivion.

[Manish @ManishSep1989]

Dhurandhar 2 was really entertaining. Do not treat this as a documentary and you will enjoy it as a movie. The only let down for me was the fight scene at the end. It was stretched too long which was not needed. Aditya dhar is the real dhurandhar here.

[Manish @ManishSep1989]

I think Vishal Bharadwaj has lost his craft. O Romeo was wrong at every level, no story, no dialogue, no acting and no music. He tried the same old Bollywood formula to try mint money. It was so bad that I could not finish the film even after fast forwarding.

[Manish @ManishSep1989]

@wrendom Why are we still playing matches with Pakistan in every icc game. Why is India and Pakistan magically appearing in the same group in every icc tournament. Where we have power we are not utilising why a foreign league would care about whom they are hiring.

[Manish @ManishSep1989]

@TansuYegen What's funny is, In sometime some politician will use the same clip to show the development and people will believe it.

[Manish @ManishSep1989]

Surya Kumar yadav is defination of eat 5 star and do nothing

[Manish @ManishSep1989]

@cgtwts I have always believed that AGI can only be achieved with organic matter and not via silica in future l. And if this is true then we are moving towards that. This is just like the Pantheon series and it's scary

[Manish @ManishSep1989]

Saju Samson 24 against Zimbabwe was praised out of proportion. Everyone is saying he gave great start and I was thinking no did not. It's just that Abhishek Sharma didn't got out. Sanju might fit better in odi yhemsn T20. Problem now is he will play against WI tomorrow

[Manish @ManishSep1989]

@Vipintiwari952 Bro why mixing the words to just gain the few likes and comments. Do not be indian media. Interviewer said that not Moin and Ravi. Inhave watched the whole interview. Guys do watch it yourself don't trust anyone here

[Manish @ManishSep1989]

https://t.co/OsDTg0XkrD

[Andrej Karpathy @karpathy]

A few random notes from claude coding quite a bit last few weeks.

Coding workflow. Given the latest lift in LLM coding capability, like many others I rapidly went from about 80% manual+autocomplete coding and 20% agents in November to 80% agent coding and 20% edits+touchups in December. i.e. I really am mostly programming in English now, a bit sheepishly telling the LLM what code to write... in words. It hurts the ego a bit but the power to operate over software in large "code actions" is just too net useful, especially once you adapt to it, configure it, learn to use it, and wrap your head around what it can and cannot do. This is easily the biggest change to my basic coding workflow in ~2 decades of programming and it happened over the course of a few weeks. I'd expect something similar to be happening to well into double digit percent of engineers out there, while the awareness of it in the general population feels well into low single digit percent.

IDEs/agent swarms/fallability. Both the "no need for IDE anymore" hype and the "agent swarm" hype is imo too much for right now. The models definitely still make mistakes and if you have any code you actually care about I would watch them like a hawk, in a nice large IDE on the side. The mistakes have changed a lot - they are not simple syntax errors anymore, they are subtle conceptual errors that a slightly sloppy, hasty junior dev might do. The most common category is that the models make wrong assumptions on your behalf and just run along with them without checking. They also don't manage their confusion, they don't seek clarifications, they don't surface inconsistencies, they don't present tradeoffs, they don't push back when they should, and they are still a little too sycophantic. Things get better in plan mode, but there is some need for a lightweight inline plan mode. They also really like to overcomplicate code and APIs, they bloat abstractions, they don't clean up dead code after themselves, etc. They will implement an inefficient, bloated, brittle construction over 1000 lines of code and it's up to you to be like "umm couldn't you just do this instead?" and they will be like "of course!" and immediately cut it down to 100 lines. They still sometimes change/remove comments and code they don't like or don't sufficiently understand as side effects, even if it is orthogonal to the task at hand. All of this happens despite a few simple attempts to fix it via instructions in CLAUDE . md. Despite all these issues, it is still a net huge improvement and it's very difficult to imagine going back to manual coding. TLDR everyone has their developing flow, my current is a small few CC sessions on the left in ghostty windows/tabs and an IDE on the right for viewing the code + manual edits.

Tenacity. It's so interesting to watch an agent relentlessly work at something. They never get tired, they never get demoralized, they just keep going and trying things where a person would have given up long ago to fight another day. It's a "feel the AGI" moment to watch it struggle with something for a long time just to come out victorious 30 minutes later. You realize that stamina is a core bottleneck to work and that with LLMs in hand it has been dramatically increased.

Speedups. It's not clear how to measure the "speedup" of LLM assistance. Certainly I feel net way faster at what I was going to do, but the main effect is that I do a lot more than I was going to do because 1) I can code up all kinds of things that just wouldn't have been worth coding before and 2) I can approach code that I couldn't work on before because of knowledge/skill issue. So certainly it's speedup, but it's possibly a lot more an expansion.

Leverage. LLMs are exceptionally good at looping until they meet specific goals and this is where most of the "feel the AGI" magic is to be found. Don't tell it what to do, give it success criteria and watch it go. Get it to write tests first and then pass them. Put it in the loop with a browser MCP. Write the naive algorithm that is very likely correct first, then ask it to optimize it while preserving correctness. Change your approach from imperative to declarative to get the agents looping longer and gain leverage.

Fun. I didn't anticipate that with agents programming feels *more* fun because a lot of the fill in the blanks drudgery is removed and what remains is the creative part. I also feel less blocked/stuck (which is not fun) and I experience a lot more courage because there's almost always a way to work hand in hand with it to make some positive progress. I have seen the opposite sentiment from other people too; LLM coding will split up engineers based on those who primarily liked coding and those who primarily liked building.

Atrophy. I've already noticed that I am slowly starting to atrophy my ability to write code manually. Generation (writing code) and discrimination (reading code) are different capabilities in the brain. Largely due to all the little mostly syntactic details involved in programming, you can review code just fine even if you struggle to write it.

Slopacolypse. I am bracing for 2026 as the year of the slopacolypse across all of github, substack, arxiv, X/instagram, and generally all digital media. We're also going to see a lot more AI hype productivity theater (is that even possible?), on the side of actual, real improvements.

Questions. A few of the questions on my mind:
- What happens to the "10X engineer" - the ratio of productivity between the mean and the max engineer? It's quite possible that this grows *a lot*.
- Armed with LLMs, do generalists increasingly outperform specialists? LLMs are a lot better at fill in the blanks (the micro) than grand strategy (the macro).
- What does LLM coding feel like in the future? Is it like playing StarCraft? Playing Factorio? Playing music?
- How much of society is bottlenecked by digital knowledge work?

TLDR Where does this leave us? LLM agent capabilities (Claude & Codex especially) have crossed some kind of threshold of coherence around December 2025 and caused a phase shift in software engineering and closely related. The intelligence part suddenly feels quite a bit ahead of all the rest of it - integrations (tools, knowledge), the necessity for new organizational workflows, processes, diffusion more generally. 2026 is going to be a high energy year as the industry metabolizes the new capability.

[Manish @ManishSep1989]

@gkcs_ Nice fake story for advertisement.

[Manish @ManishSep1989]

With Google's antigravity i was able to create a full blown agent within a few hours, which can be plugged into any database and answers your query in natural language but You do need to understand the concepts though.

[Manish @ManishSep1989]

#Dhurandhar is a regular gangwar movie wrapped in a Spy movie, which is not a bad thing as long as you do not take anything seriously.

[Akshit Singh 🇮🇳 @IndianSinghh]

Something terrible has happened in VIT Bhopal.

Private colleges are known to hide their blunders.

Either it's KIIT or VIT.

The story is same for all.

If anyone knows the entire episode , please reach out to me.

[Manish @ManishSep1989]

#TheFamilyMan3 is such a mediocre series backed by great actors and few punch lines. I always felt there is no substance available for the last two seasons. Raj and DK are just mediocre writers

[Manish @ManishSep1989]

Pratika Rawals inability to rotate strike will cost india dearly. She just takes a lot of balls to settle in without rotating the strike. So when she gets out early, it mounts a lot of pressure on other batters. During the NZ match she had played 64 dot balls out of 134 balls.

[Manish @ManishSep1989]

If @mandhana_smriti doesn't perform then they do not have a batting lineup which can take them to 280-290. @BCCIWomen need the complete restructuring and yes ban the #wpl #WomensWorldCup2025 #WomensWorldCup

[Manish @ManishSep1989]

Indian women team is half a team, Aap pehle pura ban ke aawo phir hum pura fan banege @BCCIWomen #INDvENG
#WomensWorldCup2025

[The Better India @thebetterindia]

We Have Won! No one can use ‘ORS’ on their label unless it’s a WHO-recommended formula.

This is the story of Dr. Sivaranjani Santosh, a braveheart paediatrician from Hyderabad, who fought for 8 years against sugar-rich drinks falsely marketed as ORS.

Her persistence led to FSSAI’s landmark order, protecting children and patients from misleading claims.

“These drinks had 10x the sugar WHO recommends, worsening diarrhoea and complications in millions of kids,” she explains.

This victory is not just hers, but belongs to everyone who stood with her — doctors, advocates, parents, and citizens demanding truth in labeling.

Scroll down to see how her 8-year battle changed the game for public health and children across India.

Credits : drsivaranjanionline on IG

#HealthVictory #PublicHealthIndia #ChildSafety #TruthInLabelling #FSSAI #DoctorsForChange #IndiaFightsBack

[ORS Ban India, Dr Sivaranjani Santosh, FSSAI Order, Public Health Victory, Sugar Drinks Misleading Labels]