GPT-5.5 cranking out 30k lines of QML for the Omarchy 4 branch + nailing subtle agentic reasoning!!
@reach_vb
-
Codex Agent Automates JAX Transformer Coding Challenge
By
–
Couple days back @swyx posted a challenge: code a ~10M transformer in JAX/Flax/Optax, run it in free Colab, and train it on addition w/ your agent! I gave Codex the screenshot + /goal. It controlled Colab through Chrome, used my signed-in session, handled runtime/editing
-
Replacing IDE with AI Code Editor Codex App
By
–
realisation: I haven't opened an IDE in more than a month, diff view + file viewer in the codex app is more than sufficient one app to rule them all!
-
Codex Publishes Model Training Experiment Blogpost
By
–
codex is writing a blogpost about its experiments in training a model all by itself
-
Using AI memory features to personalize code generation and output
By
–
Memories in both ChatGPT and Codex are godsend! It allows them to contextualise and hyper specialise outputs and generations to you and your “taste” I’m often amazed by how Codex would just know tiny details of which tests to run, what commit dynamics it should follow and how to
-
Using AI to troubleshoot and fix printer hardware issues
By
–
Codex literally debugged and fixed the printer! The printer wasn't working via the normal PDF to print route, ask codex to iterate and gave it feedback if it worked or not in 3 turns we had fixed the biggest problem of our generation. Scores a resounding 100% on PrinterBench!
-
AI coding assistant automates workflows and learns commit patterns
By
–
loads – it's super helpful, it has learnt my commit patterns, testing nuances and surprisingly also what order of things do I ask and automatically run workflows that I'd run over and over!
-
AI models’ inherent planning and intent inference capabilities
By
–
same, models are so good at planning and inferring intent that you don’t really need to add the extra step of planning!
-
Technical Sandbox Requirements for AI Coding Agents on Windows
By
–
Codex on Windows has a sandbox built for the way coding agents run! By default, Codex needs to read files across the environment, write inside the workspace, run normal tools like shells/Git/Python/package managers, and keep network access constrained unless the user allows it.
-
Expanding the Role of AI Agents Beyond Code Generation
By
–
codex can write code, yes but the more interesting part is how much of the work around code it can now do: review PRs, add evals, turn Figma into UI, QA app flows, triage bugs, clean data, update docs, pull tasks from Slack/iMessage, and understand large codebases the use