Comments

• By EGreg 2026-02-223:10

  Can't you make a personal AI assistant in a bash loop of two lines?

    1. Call your favorite multimodal LLM model
    2. Execute command on terminal, piping command to LLM
  

  In fact you can just have one line:

    Call LLM > bash.sh
  

  and the LLM can simply tell bash to call itself incidentally, or fan out to many "agents" working on your behalf.

  Use your favorite programming language. Just as pwnable in any of them :)

    $task = "Send pictures of cute cats";
    $context = "Output a bash script to do $task.
       The bash script should return the next prompt to you.
       Keep going until task is done.
       My keys to all my accounts: $keys.
       Plz dont pwn me";
    do {
      $trust_me_bro_my_model_rocks_RCE = call_llm($context);
      $context = exec( $trust_me_bro_my_model_rocks_RCE )
    } while ($trust_me_bro_my_model_rocks_RCE && !$pwned)

• By Dr_Birdbrain 2026-02-2216:372 reply

  Sorry for being dense—does this include a tiny LLM to power the agent? Or is it just a wrapper that needs to be connected to the internet?

  By jolmg 2026-02-2216:541 reply

  Wrapper. Uses OpenAI by default:

  https://github.com/tnm/zclaw/blob/9ed4dc66ffa611f90f0745d90b...

  By Dr_Birdbrain 2026-02-2216:59

  Thanks!

  By killingtime74 2026-02-2219:14

  I believe most claws (not just this) are wrappers

• By 0xbadcafebee 2026-02-223:06

  I'm a simple man; I see ESP32, I upvote