Durable Coroutines for TypeScript(restate.dev)

8 points by calvinfo 9 days ago | 0 comments

Restate blog post introducing Durable Coroutines in its TypeScript SDK, using generators and a deterministic scheduler for low-overhead fault-tolerant agent workflows.

Microgpt explained interactively(growingswe.com)

283 points by growingswe 8 months ago | 41 comments

Reactive Optimizers: rewrite the optimizer's source code during training(xingjianbai.com)

27 points by matt_d 23 days ago | 2 comments

Research blog post introducing OPAL, a reactive optimizer where an LLM agent monitors training dynamics and rewrites the optimizer's source code during a training run.

GPUHammer: Rowhammer attacks on GPU memories are practical(gpuhammer.com)

260 points by jonbaer 1 year ago | 89 comments

Modern Optimizers – An Alchemist's Notes on Deep Learning(notes.kvfrans.com)

27 points by maxall4 1 year ago | 1 comments

Diffusion models explained simply(seangoedecke.com)

123 points by onnnon 1 year ago | 25 comments

Dust: Pretraining Transformers Without Backpropagation(qlabs.sh)

269 points by E-Reverance 1 month ago | 79 comments

Research page from QLabs presenting Dust, a method for pretraining transformer models without backpropagation, with authors, code link, and architecture diagram.

Three new discoveries in mathematics, computer science, and physics(openai.com)

1098 points by jonluca 18 days ago | 637 comments

OpenAI post announcing AI-produced results in harmonic analysis, complexity theory (refuting ETH), and quantum field theory, and describing academic collaborations to verify them.

GPT-5.2 derives a new result in theoretical physics(openai.com)

545 points by davidbarker 9 months ago | 369 comments

OpenAI post announcing that GPT-5.2 derived a new result in theoretical physics; the captured page shows only a loading logo.

Deep learning gets the glory, deep fact checking gets ignored(rachel.fast.ai)

549 points by chmaynard 1 year ago | 134 comments

Rachel Thomas blog post on how a high-profile Nature paper using a Transformer to predict enzyme functions contained many errors that received far less attention than the original result.

Train Your Own LLM from Scratch(github.com)

376 points by kristianpaul 6 months ago | 43 comments

GitHub repository by angelos-p providing code and docs for training your own large language model from scratch.

Why your local LLM feels dumber than it is(forum.level1techs.com)

417 points by felineflock 2 months ago | 171 comments

A Level1Techs forum post presenting technical experiments on how quantization and implementation differences make locally run LLMs perform worse than reference versions.