@karpathy - AI Dynamics

Bespoke Software Era: Personalized Health Optimization Tools

By

–

19 February 2026 21h35

Very interested in what the coming era of highly bespoke software might look like. Example from this morning – I've become a bit loosy goosy with my cardio recently so I decided to do a more srs, regimented experiment to try to lower my Resting Heart Rate from 50 -> 45, over

→ View original post on X — @karpathy

19 February 2026

LLMs Transform Programming Languages and Formal Methods Constraints

By

@karpathy

–

16 February 2026 20h15

I think it must be a very interesting time to be in programming languages and formal methods because LLMs change the whole constraints landscape of software completely. Hints of this can already be seen, e.g. in the rising momentum behind porting C to Rust or the growing interest

→ View original post on X — @karpathy

16 February 2026

Code optimization: reducing line count from 234 to 200

By

@karpathy

–

12 February 2026 23h20

thank you i got a little overexcited and shipped it just a bit too soon, with a few too many brush strokes, now the internet thinks it takes 234 lines but actually it only takes 200 RIP

→ View original post on X — @karpathy

12 February 2026

Simile AI Launch: Exploring LLM Personality Dimension

By

@karpathy

–

12 February 2026 21h12

Congrats on the launch @simile_ai ! (and I am excited to be involved as a small angel.)

Simile is working on a really interesting, imo under-explored dimension of LLMs. Usually, the LLMs you talk to have a single, specific, crafted personality. But in principle, the native,… https://t.co/ObAJYvEQ8Z
— Andrej Karpathy (@karpathy) 12 février 2026

Congrats on the launch @simile_ai ! (and I am excited to be involved as a small angel.) Simile is working on a really interesting, imo under-explored dimension of LLMs. Usually, the LLMs you talk to have a single, specific, crafted personality. But in principle, the native,

→ View original post on X — @karpathy

12 February 2026

What Developers Do While AI Agents Write Code

By

@karpathy

–

01 February 2026 20h59

? what do you do while your LLM agent is writing all your code

→ View original post on X — @karpathy

1 February 2026

LLM Brain Rot: How AI Models Degrade from Low-Quality Data

By

@karpathy

–

01 February 2026 20h32

I feel like I am actively getting dumber. LLMs get brain rot and it is measurable: https://
llm-brain-rot.github.io
"continual exposure to junk web text induces lasting cognitive decline in large language models (LLMs)" why shouldn't the same be true for brains.

→ View original post on X — @karpathy

1 February 2026

Training GPT-2 Grade LLMs for Under $100

By

@karpathy

–

31 January 2026 21h55

nanochat can now train GPT-2 grade LLM for <<$100 (~$73, 3 hours on a single 8XH100 node). GPT-2 is just my favorite LLM because it's the first time the LLM stack comes together in a recognizably modern form. So it has become a bit of a weird & lasting obsession of mine to train

→ View original post on X — @karpathy

31 January 2026

Overhyping Tech Announcements: Reactions and Market Trends

By

@karpathy

–

31 January 2026 4h39

I'm being accused of overhyping the [site everyone heard too much about today already]. People's reactions varied very widely, from "how is this interesting at all" all the way to "it's so over". To add a few words beyond just memes in jest – obviously when you take a look at

→ View original post on X — @karpathy

31 January 2026