According to the tweet below, the server didn't actually run any PHP code for the first 17 hours. https://x.com/LiveOverflow/status/2114412072805208237
> Their behaviour is deterministic This isn't true for LLM generated code!
Except they don’t right? They aren’t deterministic. All the hypemaxxers over at twitter keep saying you need a way for the agent to verify the result itself. Would that be another prompt then?
Yes, but Jev & co literally cannot fail that way. It's 100%. Not the same thing.
Doesn’t surprise me. Had a layover in Copenhagen and they charged $7 for a coke.
According to the tweet below, the server didn't actually run any PHP code for the first 17 hours. https://x.com/LiveOverflow/status/2114412072805208237
> Their behaviour is deterministic This isn't true for LLM generated code!
Except they don’t right? They aren’t deterministic. All the hypemaxxers over at twitter keep saying you need a way for the agent to verify the result itself. Would that be another prompt then?
Yes, but Jev & co literally cannot fail that way. It's 100%. Not the same thing.
Doesn’t surprise me. Had a layover in Copenhagen and they charged $7 for a coke.