OpenAI · Community reports
Jev + GPT: game-agent experiments and Codex computer use
GPT revising Jev game prompts, plus a separate Codex desktop experiment. What the users reported, including failed runs.
We checked the cited posts and documentation. Measurements are attributed to their authors and have not been independently rerun by this site.
Astra works on the prompt while Jev plays
paulwei tried Jev in Slay the Spire 2 after using GPT-6 Astra. The initial post describes Astra as capable but slow and reports about 0.7 seconds of deliberation for a Jev action. That is a measurement from the author’s game setup, not an end-to-end agent latency or a result for every GPT model.
The follow-up adds an important failure: Jev’s first Ascension 10 attempt stopped at floor 6. The author says Astra then revised the prompts given to Jev, and the pair reached floor 17. The reported division of work is prompt improvement by Astra and repeated game decisions by Jev.
Sources:[3] paulwei[4] paulwei
A separate Codex experiment on the Mac desktop
Sac describes a Codex + Jev computer-use setup called Jev Use. A comparison video uses the same task, adding an event to the Mac calendar. Sac’s assessment is that the Jev version feels smoother while consuming roughly the same number of tokens.
The post does not identify the GPT model behind Codex or publish a repeated timing test. It supports a report about this desktop workflow, not a claim that every Codex task gets faster or cheaper.
Sources:[5] Sac
Faster actions did not settle the question of quality
paulwei explicitly says Jev was less capable at the game than Astra. The same thread that praises its speed also records an early failure. Reaching floor 17 after prompt revisions is progress in that experiment; it is not evidence of a completed game or a measured success rate.
Together, these reports describe two different uses of Jev around OpenAI tools: repeated game decisions guided by prompt revisions, and desktop interactions alongside Codex. They do not establish a common cost reduction, latency percentile or accuracy score.
Sources:[4] paulwei[5] Sac
Questions about Jev + GPT / Codex
Which GPT version appears in the Jev game experiment?
paulwei names GPT-6 Astra. Sac’s separate desktop post names Codex but does not identify its underlying GPT version.
Sources:[3] paulwei[5] Sac
Did Jev and GPT finish the Slay the Spire 2 run?
The cited follow-up reports reaching floor 17 on Ascension 10 after Astra revised Jev prompts. It does not report finishing the run.
Sources:[4] paulwei
Sources and reading notes
The summaries below are paraphrases. Each link opens the original source, including its surrounding context.
paulwei (@coolish)
Published:
Source checked:
[3] Trying Jev after GPT-6 Astra in Slay the Spire 2
The author describes GPT-6 Astra as capable but slow in an earlier game run, then reports roughly 0.7 seconds of action deliberation with Jev.
Personal game experiment with a video. The timing is not a controlled, repeated GPT-versus-Jev benchmark.
paulwei (@coolish)
Published:
Source checked:
[4] Astra revises Jev prompts after a failed game run
The first Ascension 10 attempt reached floor 6. The author says Astra then iterated on Jev prompts and the pair reached floor 17, while describing Jev as weaker at the game than Astra.
A follow-up from the same experiment, not independent corroboration. Reaching floor 17 is not a reported completed run.
Sac (@Saccc_c)
Published:
Source checked:
[5] Codex and Jev for adding a Mac calendar event
Sac describes a Codex + Jev computer-use experiment and compares adding the same Mac calendar event. The reported experience is smoother, with similar token consumption.
Qualitative report and comparison video. The post does not identify the underlying GPT version or give a repeatable latency measurement.