Large Language Diffusion Models(ml-gsai.github.io)

29 points by SerCe 1 year ago | 7 comments

Recursively summarizing enables long-term dialogue memory in LLMs(arxiv.org)

245 points by PaulHoule 3 years ago | 137 comments

Large Language Models as Markov Chains(arxiv.org)

63 points by Anon84 1 year ago | 33 comments

Efficient Memory Management for Large Language Model Serving with PagedAttention(arxiv.org)

87 points by jmorgan 3 years ago | 17 comments

δ-mem: Efficient Online Memory for Large Language Models(arxiv.org)

227 points by 44za12 5 months ago | 58 comments

26× Faster Inference with Layer-Condensed KV Cache for Large Language Models(arxiv.org)

112 points by georgehill 2 years ago | 16 comments

AI coding has made CI a bottleneck, so we reworked ours to keep up(linear.app)

300 points by julian_digital 1 month ago | 367 comments

A Linear engineering blog post explaining how AI-assisted coding increased CI load and how the team reworked its CI pipeline to keep up.

Some thoughts on LLMs and software development(martinfowler.com)

378 points by floverfelt 1 year ago | 347 comments

Martin Fowler's blog post sharing scattered thoughts on the state of LLMs and AI and their effect on software development.

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.

Turning GLM-5.3-Flash into a Jev-like decision model(privatemode.ai)

116 points by flxflx 1 month ago | 50 comments

Privatemode AI blog post describing how to prompt GLM-5.3-Flash so its first output token gives a decision in a single forward pass, benchmarked against Jev and Laya.

Getting AI to work in complex codebases(github.com)

442 points by dhorthy 1 year ago | 368 comments

A GitHub markdown document from HumanLayer describing advanced context engineering techniques for getting AI coding agents to work in complex codebases.

We should be more ambitious with the software we build(danluu.com)

849 points by ltratt 1 day ago | 728 comments

Dan Luu essay arguing that advancing AI coding models let developers build more ambitious software, citing pgrust, a regex engine, ripgrep fork, and board game AI projects.