openai / openai/codex

Artificial Intelligence, or Artificial Idiot?

Open
#40,997 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

app bug model-behavior windows-os
Dominant language
Rust
Stars
125k
Forks
19.4k
PR merge metrics
PR metrics pending

Description

What version of the Codex App are you using (From “About Codex” dialog)?

Desktop version

What subscription do you have?

Not sure — personal ChatGPT account

What platform is your computer?

Windows 11 on Acer laptop

What issue are you seeing?

The four AI players in my card game app, are not performing with an intelligence level of a normal human being. They behave like robots with no brain, no ability to think, analyze, utilize available information to strategize moves. For instance, they kick off a new game with a powerful pair, basically it was like "launching a nuclearn weapon for a firework show".

They dont have the ability, or even the concept that they need to profect from their photographic memory power, and use all available information to help them to evaluate, assess the game status, to unload heave weight (like a combo), to figure out what's the best move, to anticipate potenticial danger (threat such as more powerful cards still alive, or game over.

What steps can reproduce the bug?

I suspect that the four AI players planted in the app were not empowered with a human brian, if that makes any sense. Not sure how else I could explain it.

What is the expected behavior?

No response

Additional information

No response

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

No file, test, entry point, or reproducible game state is identified. First clarify whether this card-game AI behavior belongs to Codex, then provide a concrete scenario, the expected move, and the observed move so the relevant implementation can be located and validated.

Written by the indexing model from the issue text.

Assessment

Tech stack
rust
Domain
ai, desktop
Issue type
Bug
Difficulty
5/5
Estimated time
Over a week
Activity status
Active
Clarity
Needs clarification
Newbie friendliness
10/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.