Show HN: Codex Plays NetHack
asciinema.orgI'll add a link to the completed recording after the stream completes.
1 thread
Early learnings: - gpt-5.6-luna gives up too easily - /goal must be written to be hard to misinterpret ('ascend' can be interpreted as meaning to go up the stairs, thereby exiting the dungeon without playing)
gpt-5.6-sol is much more persistent - it's 36 minutes and several failures in and still going strong.