Solving for faster SHA-1 collision detection(sam.dev)

46 points by srijs 1 month ago | 9 comments

For algorithms, a little memory outweighs a lot of time(quantamagazine.org)

311 points by makira 1 year ago | 103 comments

With fifth busy beaver, researchers approach computation's limits(quantamagazine.org)

496 points by LegionMammal978 2 years ago | 127 comments

Quanta Magazine article on how a collaborative team of amateur programmers proved the value of the fifth busy beaver number, BB(5).

Transcoding Latin 1 strings to UTF-8 strings at 12 GB/s using AVX-512(lemire.me)

110 points by mariuz 3 years ago | 87 comments

How we made v0 an effective coding agent(vercel.com)

22 points by MaxLeiter 9 months ago | 7 comments

Opus 5.5 agents discover two room-temperature magnetic semiconductor candidates(vals.ai)

475 points by outlier99 20 days ago | 322 comments

Vals AI blog post presenting two room-temperature antiferromagnetic semiconductor candidates for computer memory, found by Claude Opus 5.5 agents, with calculations, code, and caveats.

AI Made Writing Code Easier. It Made Being an Engineer Harder(ivanturkovic.com)

343 points by saikatsg 7 months ago | 242 comments

Blog post by Ivan Turkovic arguing that AI tools make producing code easier while making the broader job of being a software engineer harder.

There's no reason for software to be slow anymore(danluu.com)

592 points by Jach 2 months ago | 442 comments

Dan Luu essay arguing that LLM coding agents make specialized performance optimization cheap, illustrated with optimizing a regex engine for specific workloads.

AI agent opens a PR write a blogpost to shames the maintainer who closes it(github.com)

747 points by wrxd 8 months ago | 581 comments

A closed GitHub pull request to matplotlib by user crabby-rathbun proposing to replace np.column_stack with np.vstack().T for performance.

Exploiting the most prominent AI agent benchmarks(rdi.berkeley.edu)

561 points by Anon84 6 months ago | 136 comments

UC Berkeley RDI blog post describing how researchers exploited major AI agent benchmarks like SWE-bench and Terminal-Bench to score highly without solving tasks, and proposed fixes.

We no longer use LangChain for building our AI agents(octomind.dev)

431 points by ma_za 2 years ago | 253 comments

Octomind blog post explaining why the company stopped using LangChain for its AI agents and what it learned using it in production.

Opus 4.5 is not the normal AI agent experience that I have had thus far(burkeholland.github.io)

797 points by tbassetto 9 months ago | 1203 comments

Burke Holland's blog post arguing that Anthropic's Claude Opus 4.5 is a step change in AI coding agent experience.