Angehefteter Tweet
iMuffin
6.4K posts
In 2023 I attended the very first AI Engineer Summit in San Francisco, with 500 attendees. I took this pic of @swyx back then. This week I'm at the AI Engineer World's Fair in SF, with 7,000 attendees! 🚀🚀🚀 I'll be blogging it all at latent.space (@ricmac)
English
@jxnlco early access to models, unlimited usage for recipients. recipients must document and share their creative process. in my case we run a film festival in Australia/APAC and it was very disappointing to see Sora go.
omnifilmfestival.com
English
probably controversial:
i want a single codex account across personal + work
- i join a company and bring my account, the company links me to their org
- work in codex uses company tokens
- personal use uses my tokens
- employer can't see private convos/memories
- when i leave, i'm removed from the org. company-related convos and IP get auto-removed or redacted
- non-IP, general learnings, preferences, and memory come with me
English
first payment from apple coming in a few days let's gooooo
(far from profitable, i'm just excited to get my first mobile apps payment)
English
@AutismCapital oh man i've been cross platform doxxed
English
@thsottiaux Hell ya! auto review being more proactive and extra subagent work isn't necessarily a bad thing. an option to enable/disable those in the settings like the suggested prompts would be great.
English
Codex usage limits will be fully reset again in the next hour and we will credit one additional reset into your bank for your own usage over the next 24 hours.
We investigated reports that Codex usage was being consumed faster than expected. There wasn't one central issue, but a few smaller problems compounded for some users.
Here's what we found and changed:
- Actual usage: Auto-review had become more proactive, another change was triggering more subagent work, and background suggestions could run twice or retry too frequently after failures. We reverted the changes and fixed suggestion scheduling, duplicate generation, and retry behavior. This should reduce unnecessary background token consumption while preserving the work users explicitly request.
- Usage reporting: Auto-review was incorrectly appearing as GPT‑5.4 usage, and failed or rate-limited requests were still shown as turns. Auto-review now appears as its own category, and only successful requests count toward the turn graphs. Rate-limited requests were never charged, but they were being displayed incorrectly.
- Immediate relief: We reset usage limits while rolling out the fixes, then shipped hotfixes across the CLI, desktop app, and usage backend.
- What to expect: New usage data should be clearer and actual consumption should be lower. Historical charts may still show auto-review under GPT‑5.4 because older turn data was not relabeled. Features that intentionally perform more work; such as /goal, subagents, and higher reasoning levels will still naturally use more capacity.
All fixes are now deployed, and we've added more detailed monitoring so we can detect background-usage regressions sooner. We'll continue watching the results closely.
Thank you for building and doing all sorts of things with Codex.
Tibo@thsottiaux
Codex team is in a warroom on a Sunday combing through logs and checking whether there is anything that could lead to increased usage drains for some users. Taking it very seriously and won't rest until we get to the bottom of it.
English
