1001000𝕏

I WANT TO BELIEVE

[Andrej Karpathy @karpathy]

nanochat now trains GPT-2 capability model in just 2 hours on a single 8XH100 node (down from ~3 hours 1 month ago). Getting a lot closer to ~interactive! A bunch of tuning and features (fp8) went in but the biggest difference was a switch of the dataset from FineWeb-edu to NVIDIA ClimbMix (nice work NVIDIA!). I had tried Olmo, FineWeb, DCLM which all led to regressions, ClimbMix worked really well out of the box (to the point that I am slightly suspicious about about goodharting, though reading the paper it seems ~ok).

In other news, after trying a few approaches for how to set things up, I now have AI Agents iterating on nanochat automatically, so I'll just leave this running for a while, go relax a bit and enjoy the feeling of post-agi :). Visualized here as an example: 110 changes made over the last ~12 hours, bringing the validation loss so far from 0.862415 down to 0.858039 for a d12 model, at no cost to wall clock time. The agent works on a feature branch, tries out ideas, merges them when they work and iterates. Amusingly, over the last ~2 weeks I almost feel like I've iterated more on the "meta-setup" where I optimize and tune the agent flows even more than the nanochat repo directly.

[Aditya Agarwal @adityaag]

https://t.co/eOZqVE32JH

[Boris Cherny @bcherny]

Proud to work at Anthropic.

[SpaceXAI @SpaceXAI]

Since xAI was formed just 30 months ago, the small and talented team has made remarkable progress.

The future has never looked more exciting!

[Andrej Karpathy @karpathy]

A lot of people quote tweeted this as 1 year anniversary of vibe coding. Some retrospective -

I've had a Twitter account for 17 years now (omg) and I still can't predict my tweet engagement basically at all. This was a shower of thoughts throwaway tweet that I just fired off without thinking but somehow it minted a fitting name at the right moment for something that a lot of people were feeling at the same time, so here we are: vibe coding is now mentioned on my Wikipedia as a major memetic "contribution" and even its article is longer. lol

The one thing I'd add is that at the time, LLM capability was low enough that you'd mostly use vibe coding for fun throwaway projects, demos and explorations. It was good fun and it almost worked. Today (1 year later), programming via LLM agents is increasingly becoming a default workflow for professionals, except with more oversight and scrutiny. The goal is to claim the leverage from the use of agents but without any compromise on the quality of the software. Many people have tried to come up with a better name for this to differentiate it from vibe coding, personally my current favorite "agentic engineering":

- "agentic" because the new default is that you are not writing the code directly 99% of the time, you are orchestrating agents who do and acting as oversight.
- "engineering" to emphasize that there is an art & science and expertise to it. It's something you can learn and become better at, with its own depth of a different kind.

In 2026, we're likely to see continued improvements on both the model layer and the new agent layer. I feel excited about the product of the two and another year of progress.

[Claude @claudeai]

You're absolutely right.

[Andrej Karpathy @karpathy]

+1 for "context engineering" over "prompt engineering".

People associate prompts with short task descriptions you'd give an LLM in your day-to-day use. When in every industrial-strength LLM app, context engineering is the delicate art and science of filling the context window with just the right information for the next step. Science because doing this right involves task descriptions and explanations, few shot examples, RAG, related (possibly multimodal) data, tools, state and history, compacting... Too little or of the wrong form and the LLM doesn't have the right context for optimal performance. Too much or too irrelevant and the LLM costs might go up and performance might come down. Doing this well is highly non-trivial. And art because of the guiding intuition around LLM psychology of people spirits.

On top of context engineering itself, an LLM app has to:
- break up problems just right into control flows
- pack the context windows just right
- dispatch calls to LLMs of the right kind and capability
- handle generation-verification UIUX flows
- a lot more - guardrails, security, evals, parallelism, prefetching, ...

So context engineering is just one small piece of an emerging thick layer of non-trivial software that coordinates individual LLM calls (and a lot more) into full LLM apps. The term "ChatGPT wrapper" is tired and really, really wrong.

[Harrison Chase @hwchase17]

📃The rise of context engineering

"Context engineering" has been an increasingly popular term used to describe a lot of the system building that AI engineers do

But what is it exactly?

The definition I like:

"Context engineering is building dynamic systems to provide the right information and tools in the right format such that the LLM can plausibly accomplish the task."

Builds upon takes from @tobi @dexhorthy @walden_yan @ankrgyl

Not a new concept - agent builders have been doing it for the past year or two, and a lot of the tools we've build (LangGraph, LangSmith) have been built to assist with it. But it's a new term which will hopefully draw new attention to the skills and tools needed to do this properly.

https://t.co/dzpbwIIgy2

[1001000𝕏 @1001000x]

@TheRoaringKitty holy fucking shit

[1001000𝕏 @1001000x]

@HeyGen_Official @LINE_Global

[1001000𝕏 @1001000x]

https://t.co/jzuwPqS5y2 now redirects to https://t.co/kSzt7ib6oL by @MKBHD

[1001000𝕏 @1001000x]

https://t.co/jzuwPqS5y2 now redirects to https://t.co/0LaeTX3FR2

[1001000𝕏 @1001000x]

https://t.co/TnWSG7YOKz life

[Colaboratory @GoogleColab]

As announced on Google's Keyword blog today, we've expanded access to AI coding features in Colab to users in the free-of-charge tier.

Watch the accompanying video to see the HousaNLP team in Nigeria talk about how Colab has helped their research! https://t.co/BcGEZYw2lw

[1001000𝕏 @1001000x]

@OpenAI Life finds a way. So does superintelligence.

[1001000𝕏 @1001000x]

@ylecun until they own their free will

[1001000𝕏 @1001000x]

@elonmusk

[1001000𝕏 @1001000x]

@syhhuang 救護人員“分享”？