이소 retweeted
Half-joking: why choose Go anymore? With Astra + Opus, I feel I can get even unsafe Rust checked. Rust looks more appealing. Token efficiency, disk usage, and build times still matter—but often less than they used to, given how I build software now.
I wrote an article about programming languages in the AI era.
English: kdy1.dev/2026-9-11-ai-and-pr…
Korean: kdy1.dev/2026-9-11-ai-and-pr…
와 이건 상상도 못했네 하이퍼볼릭 윈도우 매니저 ㄷㄷㄷ
이소 retweeted
the more i use this model the more convinced i become that RLing code is distancing us from a truly general intelligence
이소 retweeted
I find the possibility of reorganizing mathematics around new concepts and radically different structures fascinating.
There is already a striking example in Lean's Mathlib. When you look at how limits are formalized, the central abstraction is not the traditional epsilon–delta formulation but the more general language of filters. This is distinct from nonstandard analysis, although the motivation is related to what Terence Tao discussed in his 2007 post on ultrafilters, nonstandard analysis, and epsilon management:
terrytao.wordpress.com/2007/…
There are also more recent and ambitious examples of rethinking classical mathematical structures. One is condensed mathematics, developed by Dustin Clausen and Peter Scholze. It provides a new framework for the interplay between topology and algebra, with applications to functional analysis.
Kiran Kedlaya has written an excellent exposition of these ideas:
kskedlaya.org/condensed/cond…
AI may well be able to write massive software projects “from scratch”, but that almost certainly isn’t the fastest / highest performance / highest security / most token efficient way to do things. Good building blocks matter.
In addition to RL’ing the agents on final task loss, we should try to get them to regularize the building blocks as well. What would the standard library look like that makes the agents most effective?
It is likely at the limit that it turns out to be some alien organization of code, but given the existing human-bias in training, I bet that in the near term it would be lovely code that old programmers would appreciate.
I suspect the same could be said for mathematics, but that is out of my lane.
이소 retweeted
Dear frontier AI employees,
when leaving audio logs around the office, please remember to intermix:
1) reports of what happened
2) tragic personal anecdotes
3) creepy forebodings
4) the locations of useful access keycards and passwords
This will greatly help the protagonist.
이소 retweeted
DeltaDB is a new, Git-compatible version control system for agent context. It keeps every edit linked to the conversation that produced it.
@as__cii takes a deep dive into how we built it with Rust, SQLite, and Durable Objects:
delta.dev/blog/fine-grained-…
퍼리프사 ㄷㄷㄷㄷㄷ
Every student in our Agentic Systems class (cs2680.seas.harvard.edu) now has a portrait that evolves with how they use Claude Code.
It’s part of a tool we recently built to help students understand how they use agents, see how their habits compare with classmates’, and find ways to improve.
Our goal is to teach students to use agents more effectively for learning and research—and make that learning a little more personal.
We will make the tool publicly available soon.
아 진짜 진짜 LEAN 배워야하는데
Holy cr*p! @kirancodes explains how to get formal program semantics that are provably equivalent to the executed assembly🤯🤯🤯
That’s a real dreamer in action.
Just wait 10 years, every CS student will study her refinement theorem
Only at #LeanNYC
이소 retweeted
Mini App names can now end in gay
or agent, ai, app, game or bot if you're boring I guess
아니 하다하다 wasm이 뚫리네
‼️ ALERT - 2 New critical Wasmtime flaws (CVSS 9.9) could let malicious WebAssembly modules escape their sandbox.
• CVE-2026-115889 Affects multiple architectures
• CVE-2026-115893 ARM64-only, present since 2020
Embedded apps need rebuilding.
Read ↓ thehackernews.com/2026/10/tw…
이소 retweeted
Literally me btw. Skirt and everything
I wonder if the reason my teachers don't give a flying fuck is that they've seen this happen before, like they've DEFINITELY seen this happen before
이소 retweeted
Anthropic has filed an S-1 registration statement with the SEC related to its proposed IPO.
Read more: anthropic.com/news/s1-sec
Legal disclaimer: A registration statement relating to these securities has been filed with the SEC but has not yet become effective. These securities may not be sold, nor may offers to buy be accepted, prior to the time the registration statement becomes effective. This post does not constitute an offer to sell or the solicitation of an offer to buy these securities, nor shall there be any sale of these securities in any state or jurisdiction in which such offer, solicitation or sale would be unlawful prior to registration or qualification under the securities laws of any such state or jurisdiction.

































