Ritesh

My opinions change as I grow and evolve. 👨‍💻🎶🏕️⛹️

[Gurjot Ahluwalia @gurjota]

Just finished tax filing for a family member who's paid 23 lakhs tax in FY26, on a regular salary income of less than 50 lakhs!

Why?

Because some ESOPs vested and they get added to salary which is an absolute loot of ordinary citizens money!

Shares which are lying in a demat account, money which is not even with you is getting taxed at 30%+ plus surcharge plus cess.

INSANE TAX LAWS!

[axhiiiiii @Abhishek88548]

Student arrives 2 minutes late, misses NEET exam; daughter breaks down in tears outside the center; father says they traveled 70 km and encountered rain along the way.

Education System 💩💩

[Sahib Puniani @sahibpuniani]

@kunalb11 Kunal Shah spent 7 years teaching India to pay credit card bills through a separate app to earn coins worth nothing.

Now he runs WhatsApp.

Brace yourselves. Soon you’ll pay ₹99 to send a ❤️ and earn 5,000 WhatsApp Coins™, redeemable for absolutely nothing.

[Karthik Reddy @bykarthikreddy]

- Why does it never flood near CM DK Shivakumar's house in Sadashivnagar?

- Why does it never flood around Vidhana Soudha (except latest wonder KR Circle)?

- Why does it always flood where the middle/lower middle class stay?

Please answer @GBAChiefComm

[Deedy @deedydas]

Most software engineers are facing an identity crisis bordering on depression.

As CTOs aggressively evangelize tokenmaxxing, a class divide ensues.

The lazy. The lazy push code. They don't write it. They don't manually test it. They don't even read it. They're on autopilot. See Jira ticket, prompt for task, submit code. Many of them are barely on their computer the whole day. A comment on the PR asking why they did this? The lazy ask AI. A Slack message? The lazy ask AI. Need to prepare for standup? The lazy ask AI. As long as it sounds enough like them and isn't detected. Some of the lazy are even overemployed, and work multiple jobs. The lazy smart ones get away with this, and even rewarded. After all, software engineering for the lazy is just a dance to convince your colleagues you're smart and hard working.

The craftsmen. The craftsmen are tired. Very tired. 15 PRs in queue. Slack blowing up. The entire burden of review falls on the craftsman. The burden of understanding. They try. They work their way through the code, thoughtfully commenting to improve what ships. The response? A lazy: "That's a clever idea! You're absolutely right." with an incorrect change. It's fine, the craftsman says. I can fix them. They write a doc urging his colleagues to be better. The next day? 20,000 line PR to review. Day after day, their workload grows. Bugs seep into production. No one seems to care. Another round of AI is thrown at it. Their animosity to their colleagues rises. Eventually, they give up. It's just not what it used to be. The craft they loved is dead. They eventually wake up, a lazy.

This isn't all companies. Many companies are genuinely more productive, adopt the right set of principles and practices around AI development and have highly talented teams that trust each other. It tends to happen in bigger companies that are 10+yrs old with a higher talent variance. But it happens. A lot.

[Claude @claudeai]

We're bringing the advisor strategy to the Claude Platform.

Pair Opus as an advisor with Sonnet or Haiku as an executor, and get near Opus-level intelligence in your agents at a fraction of the cost.

[Claude @claudeai]

New in Claude Code: auto mode.

Instead of approving every file write and bash command, or skipping permissions entirely, auto mode lets Claude make permission decisions on your behalf.

Safeguards check each action before it runs.

[Andrej Karpathy @karpathy]

Software horror: litellm PyPI supply chain attack.

Simple `pip install litellm` was enough to exfiltrate SSH keys, AWS/GCP/Azure creds, Kubernetes configs, git credentials, env vars (all your API keys), shell history, crypto wallets, SSL private keys, CI/CD secrets, database passwords.

LiteLLM itself has 97 million downloads per month which is already terrible, but much worse, the contagion spreads to any project that depends on litellm. For example, if you did `pip install dspy` (which depended on litellm>=1.64.0), you'd also be pwnd. Same for any other large project that depended on litellm.

Afaict the poisoned version was up for only less than ~1 hour. The attack had a bug which led to its discovery - Callum McMahon was using an MCP plugin inside Cursor that pulled in litellm as a transitive dependency. When litellm 1.82.8 installed, their machine ran out of RAM and crashed. So if the attacker didn't vibe code this attack it could have been undetected for many days or weeks.

Supply chain attacks like this are basically the scariest thing imaginable in modern software. Every time you install any depedency you could be pulling in a poisoned package anywhere deep inside its entire depedency tree. This is especially risky with large projects that might have lots and lots of dependencies. The credentials that do get stolen in each attack can then be used to take over more accounts and compromise more packages.

Classical software engineering would have you believe that dependencies are good (we're building pyramids from bricks), but imo this has to be re-evaluated, and it's why I've been so growingly averse to them, preferring to use LLMs to "yoink" functionality when it's simple enough and possible.

[Claude @claudeai]

You can now enable Claude to use your computer to complete tasks.

It opens your apps, navigates your browser, fills in spreadsheets—anything you'd do sitting at your desk.

Research preview in Claude Cowork and Claude Code, macOS only.

[Daniel Hnyk @hnykda]

LiteLLM HAS BEEN COMPROMISED, DO NOT UPDATE. We just discovered that LiteLLM pypi release 1.82.8. It has been compromised, it contains litellm_init.pth with base64 encoded instructions to send all the credentials it can find to remote server + self-replicate. link below

[Ujjwal Chadha @ujjwalscript]

Your AI Agent is mathematically guaranteed to FAIL.

This is the dirty secret the industry is hiding in 2026. Everyone on your timeline is currently bragging about their "Multi-Agent Swarms."
Founders are acting like chaining five AI agents together is going to replace their entire engineering team overnight.

Here is the reality check: It’s a mathematical illusion.

Let’s look at the actual numbers.
Say you have a state-of-the-art AI agent with an incredible 85% accuracy rate per action. In a vacuum, that sounds amazing.

But an "autonomous" workflow isn't one action. It’s a chain.

Read the ticket ➡️ Query the DB ➡️ Write the code ➡️ Run the test ➡️ Commit. Let's do the math on a 10-step process:
$0.85^10= 0.19$

Your "revolutionary" autonomous system has a 19% success rate.

And the real-world data proves it. Recent studies out of CMU this year show that the top frontier models are failing at over 70% of real-world, multi-step office tasks.

We are officially in the era of "Agent Washing." Startups are rebranding complex, buggy software as "autonomous agents" to look cool, but they are ignoring the scariest part: AI fails silently.

When traditional code breaks, it crashes and throws a stack trace.

When an AI agent breaks, it doesn't crash. It just confidently hallucinates a fake database entry, sidesteps a broken API by faking the response, and keeps running—corrupting your data for weeks before you notice.

If your "automated" system requires a senior engineer to spend three hours digging through prompt logs to figure out why the bot made a "creative decision," you didn't save any time. You just invented a highly expensive, unpredictable form of technical debt.

Stop trying to build fully autonomous swarms to replace human judgment.
Start building deterministic guardrails where AI is the engine, but the engineer holds the steering wheel

[Garry Tan @garrytan]

MCP sucks honestly

It eats too much context window and you have to toggle it on and off and the auth sucks

I got sick of Claude in Chrome via MCP and vibe coded a CLI wrapper for Playwright tonight in 30 minutes only for my team to tell me Vercel already did it lmao

But it worked 100x better and was like 100LOC as a CLI

[Arnav Gupta @championswimmer]

I was not always hopeless about India. I spent 8-9 years of my professional years there, while at least 30% of my college batchmates left right during graduation and the number was close to 70% in 5 years.

But when any efforts to improve things by identifying what’s wrong is met with violent and vitriolic response from people (who have most likely not contributed even 10% of what I have back to the country), and this incessant “anti national” cry, it gets easier to give up and move on and convince yourself that those people just deserve what they get and you don’t need to suffer it along with them.

[CG @cgtwts]

Kimi releases Kimi Claw:

- 40GB cloud space
- 5,000+ community skills
- works 24/7
- pro-grade live data search
- OpenClaw integration ( third party)

[Akshay 🚀 @akshay_pachaar]

MiniMax-M2.5 is now fully open source.

Think Opus 4.6 but 95% cheaper.

Download model weights: https://t.co/Nk7LzmExv8

GitHub: https://t.co/Zsu3TD4N7z

[Boris Cherny @bcherny]

@big_duca Someone has to prompt the Claudes, talk to customers, coordinate with other teams, decide what to build next. Engineering is changing and great engineers are more important than ever.

[Ritesh @krriteshgupta]

Well .. well .. well !!

[David Ondrej @DavidOndrej1]

https://t.co/hvec7e4OI7

[David Ondrej @DavidOndrej1]

https://t.co/hvec7e4OI7

[🚨Indian Gems @IndianGems_]

Death certificate of average Indian

>Died from drinking water
>Died from eating paneer
>Died from drinking milk
>Died from breathing Air
>Died from falling in pit/potholes
>Died from falling in drain
>Died from speeding car
>Died from taking medicine
>Died from Chinese manjha

[Nehr_who? @Nher_who]

- He didn't go to Manipur which is under fire

- He didn't go to Indore where 25 ppl died due to contamination

But he skipped all his work to attend his DD News anchor Ashok daughter’s wedding.

Because attending Bootlicker's wedding is more Important than Human's life.