Jithin Anchanattu (h/eng)

Not on Twitter for anyone’s approval. Retweets are not endorsements. #TechEvangelist #Rajagirian #BeliveInPeople

[Jithin Anchanattu (h/eng) @getjithin]

You don't write the code - the vibe writes through you. #WordOfTheYear

[Andrej Karpathy @karpathy]

There's a new kind of coding I call "vibe coding", where you fully give in to the vibes, embrace exponentials, and forget that the code even exists. It's possible because the LLMs (e.g. Cursor Composer w Sonnet) are getting too good. Also I just talk to Composer with SuperWhisper so I barely even touch the keyboard. I ask for the dumbest things like "decrease the padding on the sidebar by half" because I'm too lazy to find it. I "Accept All" always, I don't read the diffs anymore. When I get error messages I just copy paste them in with no comment, usually that fixes it. The code grows beyond my usual comprehension, I'd have to really read through it for a while. Sometimes the LLMs can't fix a bug so I just work around it or ask for random changes until it goes away. It's not too bad for throwaway weekend projects, but still quite amusing. I'm building a project or webapp, but it's not really coding - I just see stuff, say stuff, run stuff, and copy paste stuff, and it mostly works.

[Unreal Engine @UnrealEngine]

Unreal Engine 5.8 ships today with experimental MCP server support:

Your sources, your pipeline and your workflow—simply configure the MCP plugin and connect to any agent. Get familiar with the MCP server and the PCG Primitive Plugin today and see what teams can build together: https://t.co/cDITLWWv2F

[Mike I Creative Mints @creativemints]

Yesterday @framer 3.0 landed and my plans for a good night's sleep immediately went out the window :) I jumped straight into the 24 hour hackathon, found a topic, brought AI agents on board, and learned a ton along the way

Jump into the thread and I'll show you everything!🧵

[La Sagrada Família @sagradafamilia]

We see the tower of Jesus Christ illuminated for the first time!
The light show, starting from the base up to the illumination of the cross, culminated with a composition of lights guided by drones that traced the figure of Gaudí and the phrase “first love, then technique”.

[sanjoy ghose @advsanjoy]

I can bet my bottom dime that the Delhi Police shall deny him permission to have a cockroach protest in Jantar Mantar on June 6th. I can also reasonably foresee a preventative detention as was done for Sonam Wangchuk! This govt is not like the UPA which allowed civil society to freely protest and then paid a heavy price for it. This is the same reason why it doesn’t make its ministers take public accountability and resign!

[Thariq @trq212]

been asking others at Anthropic how they stay in the loop with Claude and fully understand the work being done

this is one of my favorites from Suzanne:

[Mike Piccolo @mfpiccolo]

https://t.co/GK1ojr8Opb

[Jithin Anchanattu (h/eng) @getjithin]

@OlaEV_Support I didn't get any calls from anyone. No service champion called me or informed me about any solution for my Ola EV problems.

[Jithin Anchanattu (h/eng) @getjithin]

@OlaEV_Support it's been more than 5+ months now. What's your SLA to fix this issue? Give me an ETA or contact details of a customer care spokesperson.

[OlaEV_Support @OlaEV_Support]

@getjithin Hello, we are working on solving your issue on priority, we will soon update you on this. https://t.co/9GYef5CSWT

[Jan 🏴󠁧󠁢󠁳󠁣󠁴󠁿 @RosaryMum]

“If we really understood the Mass, we would die of joy.”

St. John Vianney

[Ronin @DeRonin_]

Andrej Karpathy: "90% of Claude's mistakes come from missing context, not a weak model."

41% mistake rate without a CLAUDE.md. 11% with the 4-rule baseline. 3% with the 12-rule version below

here are the 12 rules senior engineers settled on:

1. think before coding: state assumptions, don't guess. the model can't read your mind, stop hoping it will

2. simplicity first: minimum code, no speculative abstractions. the moment you let Claude add "for future flexibility," you've added 200 lines you'll delete next quarter

3. surgical changes: touch only what you must. don't let it improve adjacent code, that's how PRs blow up

4. goal-driven execution: define success criteria upfront, loop until verified. without them Claude either loops forever or stops too early

5. use the model only for judgment calls: classification, drafting, summarization, extraction. NOT routing, retries, status-code handling, deterministic transforms. if code can answer, code answers

6. token budgets are not advisory: per-task 4000, per-session 30000. by message 40 of a long debug, Claude is re-suggesting fixes you rejected at message 5

7. surface conflicts, don't average them: two patterns in the codebase? pick one. Claude blending them is how errors get swallowed twice

8. read before you write: read exports, callers, shared utilities. Claude will happily add a duplicate function next to an identical one it never read

9. tests verify intent, not just behavior: a test that can't fail when business logic changes is wrong. all 12 of Claude's tests can pass while the function returns a constant

10. checkpoint every significant step: Claude finished steps 5 and 6 on top of a broken state from step 4. nobody noticed for an hour

11. match the codebase conventions: class components? don't fork to hooks silently. testing patterns assumed componentDidMount, hooks broke them without surfacing

12. fail loud: "completed successfully" with 14% of records silently skipped is the worst class of bug. surface uncertainty, don't hide it

what actually compounds instead of the next framework:

- the CLAUDE.md file as institutional memory across sessions
- eval-driven changes, not vibe-driven
- checkpoints over speed
- explicit conflicts over silent blending
- discipline over framework, every time
- one repo, one rules file, no exceptions

be a few rules ahead of AI twitter before this becomes mass-opinion

study this

[Vaishnavi @_vmlops]

This is the best site on the internet to learn harness engineering

https://t.co/n8bV1yKSTS

[Nihal Pasham @npashi]

Finally able to talk about what I've been heads-down on for 6 months at @nvidia 🦀⚡

We just open-sourced cuda-oxide — an experimental rustc backend that lets you write CUDA kernels in pure Rust.

No DSLs. No FFI. No source-to-source step. Single source.

Short🧵👇

[Jithin Anchanattu (h/eng) @getjithin]

@ola_supports @OlaEV_Support @OlaElectric

[Jithin Anchanattu (h/eng) @getjithin]

@ola_supports

My Ola S1 has been stuck at your service center since Dec 2025 due to repeated battery failures. Multiple temporary repairs have already failed.

Your support team called once after my complaint in x platform, but there has been no action, update, or resolution.

[Catholic Sat @CatholicSat]

The Pope’s Prayer intention for the month of May is for an end to food waste and that everyone has access to food.

“Awaken in us a new awareness that we learn to thank you for every food, to consume simply, to share with joy, and to care for the fruits of the earth as a gift from you, destined for all, not just a few.”

[Jithin Anchanattu (h/eng) @getjithin]

My Ola S1 has been at the service center since Dec 2025 (over 5 months), and it's still unusable.

The same battery issue repeated multiple times. No fix. No timeline. Escalated to @OlaElectric @ola_supports, but there has been no response, not even a reply.

@bhash

[Rahul @sairahul1]

Karpathy didn't make a course.

He made THE course.

3 hours. Free.

Tokenization. Attention. Hallucinations. Tool use. RLHF. DeepSeek. AlphaGo.

Every behavior you've ever wondered about in an LLM - where it comes from, why it exists, how it was engineered.

The gap between engineers who understand this and engineers who don't isn't technical depth.

It's the ability to conceive of entirely different things.

[Allen Braden @allen_explains]

This 2-hour Stanford lecture breaks down how models like ChatGPT and Claude are actually built, clearer than what many people in top AI roles ever get exposed to.

Save this and set aside two hours today. It might end up being the most valuable thing you learn all week.

[Jithin Anchanattu (h/eng) @getjithin]

On point!

[Andrej Karpathy @karpathy]

Someone recently suggested to me that the reason OpenClaw moment was so big is because it's the first time a large group of non-technical people (who otherwise only knew AI as synonymous with ChatGPT as a website) experienced the latest agentic models.

[Jithin Anchanattu (h/eng) @getjithin]

@AskKubeir Happy Easter 🥳