[trq_]

This is awesome, can't wait for evals against Claude Computer Use!

[amelius]

Can we first test this with basic sysadmin work in a simple shell?

Can't wait to replace "apt get install" by "gpt get install" and then have it solve all the dependency errors by itself.

[ErikBjare]

This had been possible for a year already. My project gptme does it just fine (like many other tools), especially now with Claude 3.5.

[amelius]

I know that it exists. I was just hoping we can make such interactions (practically) bug-free before we move on to the next big thing.

[anonym29]

Threat actors can't wait for you to start doing this either.

[asdev]

how can you write metrics against something that's non deterministic?