the experience will get better but here’s something that’d help: 1. create a goal md and put your ramblings there
2. ask codex to use set_goal and refer to goal md and ask for approval from you before it gets set go all through compactions codex will refer to your “ramblings”
@reach_vb
-
Using goal.md and set_goal with codex for compactions
By
–
-
Success with Codex: Convert Writing Samples into a Skill
By
–
it’ll get better sooner thank you think but later than you want! in the meantime I’ve had tremendous success by give codex samples of writings and artefacts that I like and having it convert that into a skill use that skill for whenever it writes (ask codex to add it to your
-
AI shaves 15% off dev docs build time via automated PR and checks
By
–
/goal literally shaved off 15% from our dev docs build time – it created a PR and verified build times all whilst using chrome extensions to do spot checks on the rendered UI Worked for 5 hours in total and landed some great optimisations Not merged yet, but incredible to see
-
Codex tip: use plugins to boost power, just ask Codex
By
–
Codex tip: one of the easiest ways to make Codex much more powerful is openai/plugins
there are now 100+ plugins for everything from building apps to working with Figma, Notion, Vercel, and more the best part: you do not even need to know which ones exist
open Codex and ask: -
Skeptical CLI user becomes tribalistic after dogfooding Codex app
By
–
When I joined OpenAI, the codex app was still in its early days of being put together and being a staunch CLI user I was quite sceptical! All of that changed when I started dogfooding the app, and within days started feeling this tribalistic instinct to try and delegate as much
-
Improving DX for OpenAI API, SDKs and platform – seeking feedback
By
–
going to focus the next few weeks on improving DX for OpenAI API, SDKs and platform, what could be better? what are some papercuts and nothing is too small – docs, tutorials, guides, cookbook hit me up with all 🙂
-
Codex Python SDK enables mid-stream message steering
By
–
Codex Python SDK is quite powerful, you can even steer messages mid-stream!
-
Codex() starts local app-server, no new Node process per input
By
–
no, it does not spawn a new Node process per input. Codex() starts a local Codex app-server process and the SDK talks to it over stdio/JSON-RPC for threads and turns.
-
Resume restores persisted conversation history but not live processes
By
–
Resume restores the persisted thread: conversation/run history plus thread settings/config that are saved with it. It does not resurrect live tool/process state. So if Codex changed files, those filesystem changes are still there. But open shell processes, transient handles,
-
Codex now supports Amazon Bedrock with GPT-5.4 and GPT-5.5
By
–
PSA: Codex now works with Amazon Bedrock! To configure, set: model_provider = "amazon-bedrock" and Codex can run local CLI, desktop, and IDE workflows against OpenAI models on Bedrock, using AWS-native auth/IAM. Both GPT-5.4 and GPT-5.5 are supported. Big unlock for teams