Burkov's True Positive Weekly #183: RAG in fintech, GRPO search agents, 14-byte nets
burkov · x · 2026-10-23
Andriy Burkov published issue #183 of his True Positive Weekly AI newsletter. Highlights include:
- A tutorial on being more ambitious, for humans with models
- Whether autoregressive diffusion can generate market data
- Tokenomics: quantifying where tokens go in agentic software engineering
- 1.5 years of RAG in fintech: what actually worked after early screwups
- Explainer on training search agents with GRPO
- Projects: beating Warcraft III's hardest AI with self-play RL on one desktop; a 14-byte neural network solving a maze
- Toto 2.0, a time series foundation model
More from coding & agent
- Decisions API hits GA as agents automate cloud video editing via feedback loops — dkundel · 2026-10-23
- Swarms API changelog: 8 months of streaming, multi-agent orchestration, and dynamic model pricing — KyeGomezB · 2026-10-23
- A curated library of 50+ free AI agent resources: videos, repos, one Google Doc — ifioknkem · 2026-10-23
- Vercel adds no-account deploys: drag and drop a file to get a live URL — steren · 2026-10-23
- Dev runs 5 Claude Code sessions that coordinate via MCP Agent Mail to root his network cameras — doodlestein · 2026-10-23
- Vercel ships 'vercel deploy --temporary' for ephemeral agent-built deployments — cramforce · 2026-10-23