Codex Engineer Requests Feedback on Tool Switch
OpenAI Codex engineer Tibo asks users for feedback on switching to the tool.
Tibo, Research Engineer and Engineering Lead on OpenAI's Codex team, posted seeking reasons users switched to Codex along with likes and suggested improvements. The post instructed readers not to say reset. A follow-up reply from the same account stated not to mention Linux because the team just shipped that support. Daniel Jeffries replied that Codex can stay on target for 10 or 12 hours autonomously with strong cross-conversation memory, likening it to a leap from Level 3 to Level 4 self-driving.
Why did you switch to Codex? What do you like about it and what could we improve? Don’t say reset.
Combined views
1.4M
7 posts, first seen 12d ago
Reactions from ranked influencers
6 postsAlso don’t say Linux, we just shipped that.
@thsottiaux It's ability to stay on target for 10 or 12 hours autonomously is incredible. Feels like a leap from Level 3 to Level 4 self driving. It's general memory system is incredibly strong and it always seems to remember across conversations.
@thsottiaux Minor QoL thing, but it seems like the load time for threads got much longer with a recent update. Or are you just trying to make sure we see the logo for a few seconds now :)
@thsottiaux it’s snappy, feels smarter, the apps on Mac and iPhone are much better than Claude now, computer use works great
@thsottiaux Why can't i change effort in ephemeral btw sessions