Topic

Code Generation

All digests tagged Code Generation

Suggested route

Topic journey

Move from earlier context through the available material to the newest signals. This route is a reading aid, not a difficulty ranking.

Start here

Stanford CS329A Self-Improving AI Agents | Part 4 | Learning from Feedback with Tools/Code Aug 3, 2026 · 1:11:13 This lecture covers three approaches to improving LLMs: ReAct (reasoning + tool calling), RLEF (coding agents using execution feedback), and Constitutional AI (self-critique).

Recent signals

Agentic Search vs Vector Search for Coding Agents: We Ran the Eval — Braintrust Oct 5, 2026 · 18:15 Comparing agentic search vs. vector search for coding agents, this talk reveals that while both methods achieved equal accuracy, vector search cost four times more due to lack of connective context.

AI Engineer

Agentic Search vs Vector Search for Coding Agents: We Ran the Eval — Braintrust

Comparing agentic search vs. vector search for coding agents, this talk reveals that while both methods achieved equal accuracy, vector search cost four times more due to lack of connective context.

Read article

Stanford Online

Stanford CS329A Self-Improving AI Agents | Part 4 | Learning from Feedback with Tools/Code

This lecture covers three approaches to improving LLMs: ReAct (reasoning + tool calling), RLEF (coding agents using execution feedback), and Constitutional AI (self-critique).

Read article