True Positive Weekly #183
True Positive Weekly #183
The most important artificial intelligence and machine learning news and articles
Hey, in this issue: How to be more ambitious: A tutorial for humans with models; Can you use autoregressive diffusion to generate market data?; Quantifying where tokens are used in agentic software engineering; RAG in fintech, what actually worked after screwups; Training search agents with GRPO; A 14-byte neural network solves a maze; and more.
This newsletter has no ads. Please support my regular work on curating this newsletter (and my work as a book author) by becoming a Cool Supporter 🚀
How to be more ambitious: A tutorial for humans with models
Tokenomics: Quantifying where tokens are used in agentic software engineering
[Experience] 1.5 years of RAG in fintech, what actually worked after screwups
[Explained] Training search agents with GRPO
[Project] Beating Warcraft III’s hardest AI with self-play reinforcement learning on one desktop
[Project] A 14-byte neural network solves a maze
[Model] Toto 2.0: A time series foundation model
Like or comment to help the newsletter grow.
© 2026 Andriy Burkov
410-117 Quai St-André, Quebec City (QC) Canada