✳flâneur — a map of the web's best reading
Using Goals in Codex
developers.openai.com · 3,149 words · saved by 1 readers
Goals are persistent objectives in Codex that keep a thread working toward a defined outcome across turns. A Goal gives Codex a completion c
Goals are persistent objectives in Codex that keep a thread working toward a defined outcome across turns. A Goal gives Codex a completion condition: what should be true, how success should be checked, and what constraints must stay intact. Codex already works well for well-scoped coding tasks: inspect a repository, fix a bug, add a test, explain a failure, or implement a focused change. Goals are for tasks where the next step depends on what Codex learns along the way: profiling, patching, benchmarking, reproducing a flaky test, or turning a research question into an evidence-backed audit. Th
Explore this link on the map →saved by
related reading
- Best practices for Claude Code - Claude Code Docsanthropic.com
- Shipping at Inference-Speed | Peter Steinbergersteipete.me
- A Guide to Claude Code 2.0 and getting better at using coding agents – sankalp's blogsankalp.bearblog.dev
- Co-Creating Life Goals from Everyday Computer Usearxiv.org
- Research Objectives | Definition & Examplesscribbr.com
- Goal Factoring — LessWronglesswrong.com
- Lecture 01. Strong Models Don't Mean Reliable Execution | Learn Harness Engineeringwalkinglabs.github.io
- How I Manage Projects and Goals in Obsidian | Christian B. B. Houmannbagerbach.com
- Effective harnesses for long-running agents \ Anthropicanthropic.com
- Building self-improving tax agents with Codex | OpenAIopenai.com
- Killing Coding Agent Slop With Adversarial Self-Playusetelos.ai
- GitHub - multica-ai/andrej-karpathy-skills: A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. · GitHubgithub.com