AI only works reliably when it's wrapped in real code
Quote
you're asking a question. that the agent doesn't already know a pattern of language for. then there's no way that you'll ever get out of the model that thing that you want.
Episode 261: Podhemian Grove (episode page, opens in a new tab) 00:16:07 (play audio from this timestamp, opens in a new tab)
Voice-matched
Summary
If you ask an agent something it has no language pattern for, like how many R's are in 'strawberry' or a math problem, the model alone can't reliably get it right. The only dependable way is for it to write and run code to check. Since that's too costly to do every time, the reality setting in is that you have to build deterministic guardrail software around these models.
Not in the audio. Guest episode (Mike Dell; 0.35 voice threshold). The quote is the start of a 6-cue Dave run answering Adam's question about using robots for coding.
Also said
Episode 261: Podhemian Grove (episode page, opens in a new tab) 00:13:05 (play audio from this timestamp, opens in a new tab)
not. you have to the reality has set in that you have to build guardrail systems around these things.
Voice-matched