Lenny RachitskyHost of Lenny's Podcast | Author of Lenny's Newsletter

The biggest trap in evals

27 Sept 2025 · 0 min

Watch on YouTube

0:21

Short excerpt from a YouTube video (‘The biggest trap in evals’ by Lenny Rachitsky) warning against automating error analysis with large language models. The speaker advises that LLMs often lack the contextual understanding needed to reliably detect product-level issues or 'product smell,' and recommends manual evaluation for error analysis tasks.

Number one pitfall right here is people are like, let me automate this with an LLM. 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 bad product smell or not. So I think in these cases, it's so important to make sure you are manually doing this yourself.