error analysis

3 statements across 1 episodes · 0 bullish · 1 bearish · 2 people on the record · first statement Sep 25, 2025 by Shreya Shankar · across every show →

Everything said about error analysis, oldest first

Sep 25, 2025 negative
Insight
Shankar: LLMs fail at initial error analysis due to missing context
“What we usually find when we try to ask an LLM to do this error analysis is it just says the trace looks good because it doesn't have the context needed to understand whether something might be, you know, bad product smell or, you know, not”
Shreya Shankar Sep 25, 2025 ▶ 24:05 Why AI evals are the hottest new skill for product builders | Hamel Husain & Shreya Shankar
Sep 25, 2025
Insight
Husain: Log only the single most upstream error per trace
“Just write down the first thing that you see that's wrong. The most upstream error. Don't worry about all the errors. Just capture the most, the first thing that you see that's wrong and stop and move on.”
Hamel Husain Sep 25, 2025 ▶ 22:14 Why AI evals are the hottest new skill for product builders | Hamel Husain & Shreya Shankar
Sep 25, 2025 neutral
Insight
Husain: Jumping straight to evals without error analysis derails AI products
“You want to usually ground yourself in your actual errors. You don't want to skip this step. And so the reason I'm kind of spending so much time on this is like, this is where people get lost. They go straight into evals. Like, let me just write some tests. An…”
Hamel Husain Sep 25, 2025 ▶ 47:00 Why AI evals are the hottest new skill for product builders | Hamel Husain & Shreya Shankar
Made with StarZero

Turn any episode into a week of clips.

This entire site, over 300 episodes transcribed, diarized, checked and made playable, runs on the StarZero media pipeline. Drop in your own episode and the podcast clipper finds the moments worth sharing, cuts them, captions them, and reframes them for every feed.