Larry Li

[Thomas Sowell Quotes @ThomasSowell]

“Socialists don't like ordinary people choosing, for they might not choose socialism.”

— Margaret Thatcher

[Fermat's Library @fermatslibrary]

Carl Sagan

[Lenny Bogdonoff @rememberlenny]

TIL

[Andrej Karpathy @karpathy]

This is a new paradigm for interacting with Claude that is significantly more "inline" with all the other human activity org-wide. Once you do all of the under the hood engineering work to make this "just work" (e.g. across tools, integrations, compute environments, memory, security, etc.), Claude basically joins the team in a seamless way - you can talk to it as you would talk to a person and it can help with a very large variety of workloads.

Imo this is the 3rd major redesign of LLM UIUX. The first paradigm was that the LLM is a website you go to, the second was that it is an app you download to your computer. This third one is that it is a self-contained, persistent, asynchronous entity with org-wide tools and context, working alongside teams of humans. It really takes a while to wrap your head around it, but it works and it is awesome.

[Andrej Karpathy @karpathy]

This is a super exciting release - Claude Fable 5 is the same underlying model as Mythos but with added safeguards. The benchmarks are great and it's SOTA on everything by a margin but I'll add that *qualitatively* also, this is a major-version-bump-deserving step change forward (imo of the same order as Claude 4.5 was in November), peaking especially for long problem-solving sessions on very difficult problems. You can give it a lot more ambitious tasks than what you're used to, the model "gets it" and it will just go, and it's never felt this tempting to stop looking at the code at all (but don't do this in prod!). The model still has quirks that people will run into and the safeguards are configured to be a little too trigger happy for launch, which can hopefully be tuned over time.

I feel a lot of things changing as working software increasingly comes out on a tap. The Jevon's paradox kicks in and I feel my own demand for software growing substantially. You can ask for anything - explainers, visualizers, dashboards, bespoke single-use apps (e.g. a full wandb that is hyper-specific just for your project), you can 10X your test suite, auto-optimize code, run giant research projects with custom HTML for the results, anything! "Free your mind" (Matrix ref). Really looking forward to all the things people build!

[Andrej Karpathy @karpathy]

Personal update: I've joined Anthropic. I think the next few years at the frontier of LLMs will be especially formative. I am very excited to join the team here and get back to R&D. I remain deeply passionate about education and plan to resume my work on it in time.

[Max Lv @m0d8ye]

写了篇长文总结了一下所有发现。给这个 thread 结个尾：https://t.co/YGNkNJZOm9

[Nancy.W  @heynancy45]

“威权下也能有创新”，解释了困扰我很久的天朝人为什么骄傲——把苦难当作蜜糖把枷锁当作时尚。

[Thariq @trq212]

a prompt I've been using a lot recently:

implement <SPEC> and while you do, keep a running implementation-notes.html file (or markdown) with decisions you had to make weren't in the spec, things you had to change, tradeoffs you had to make or anything else I should know

[Thinking Machines @thinkymachines]

People talk, listen, watch, think, and collaborate at the same time, in real time. We've designed an AI that works with people the same way.

We share our approach, early results, and a quick look at our model in action.

https://t.co/AFJZ5kH7Ku

[Thariq @trq212]

https://t.co/MXt5XS4xBX

[Mikhail @NotTulip]

康熙亲征葛尔丹，路过陕西，给总管太监写信吐槽说陕西虽然风俗醇厚，但“城堡都在山顶上，村庄都在破崖旁，做洞居住，岭不成岭，道不成道，可笑之极。”

[Erik Meijer @headinthebox]

Was chatting with Gemini about Synthetic Domain Theory, and it mentioned Squiggol, then this happened:

Wait—are you Erik Meijer?

If so, it is an incredible honor to be chatting with you! Your work on "Functional Programming with Bananas, Lenses, Envelopes and Barbed Wire" [1] basically defined the "Algebra of Programming" for an entire generation.

Ego stroking aside, I think this is a quite remarkable sign of how much knowledge is stored in these LLMs.

[dany @danywander]

y'all been asking for a rainy and moonlight modes.
i made them.

if you're on desktop, press
[D] for day mode,
[S] for sunny mode,
[N] for night mode,
[M] for moonlight mode,
[R] for rainy mode or
[C] to crash the website — and [C] again to restore it.

if you’re on mobile, just tap each letter of my logo.
keep in mind that A and N you can tap again to switch into more modes.

https://t.co/mOL410GW0A

[Cheng Lou @_chenglou]

My dear front-end developers (and anyone who’s interested in the future of interfaces):

I have crawled through depths of hell to bring you, for the foreseeable years, one of the more important foundational pieces of UI engineering (if not in implementation then certainly at least in concept):
Fast, accurate and comprehensive userland text measurement algorithm in pure TypeScript, usable for laying out entire web pages without CSS, bypassing DOM measurements and reflow

[Evan (Yifeng) Wang @ewind_dev]

非常开心基于 @jakevin7 的 OpenCLI，跑通了一个本地版的个人 Google！

直接用本地的 claude / codex 搜索各大平台上收藏的推文、GitHub 点赞等信息，还能聚合搜索和它们的聊天 session，这不就是面向个人的本地搜索引擎吗！

Spool 已经开源，欢迎体验！上链接 👇

[Matt Pocock @mattpocockuk]

Good tip for avoiding cognitive debt in codebases where AI has run wild:

Design the interface, delegate the implementation

[Larry Li @realLarryLi]

深有同感，一种 Vibe/Agentic Coding Fatigue

JavaScript: First time?

[Mario Zechner @badlogicgames]

I'm usually not one to write thought pieces without much technical depth. But here we go.

Slow the fuck down.

https://t.co/dcOwPK357F

[Marc Andreessen 🇺🇸 @pmarca]

My information consumption is now 1/4 X, 1/4 podcast interviews of the smartest practitioners, 1/4 talking to the leading AI models, and 1/4 reading old books. The opportunity cost of anything else is far too high, and rising daily.

[Boris Cherny @bcherny]

👋 Roughly, the more tokens you throw at a coding problem, the better the result is. We call this test time compute.

One way to make the result even better is to use separate context windows. This is what makes subagents work, and also why one agent can cause bugs and another (using the same exact model!) can find them. In a way, it’s similar to engineers — if I cause a bug, my coworker reviewing the code might find it more reliably than I can.

In the limit, agents will probably write perfect bug-free code. Until we get there, multiple uncorrelated context windows tends to be a good approach.