• Users often do not want the thing you are optimizing. A meeting-summary team argued over three- versus five-sentence summaries; users did not care about the summary at all, only the action items assigned to them.
• LinkedIn's skill-fit bot taught them users want helpful, not correct. "You are a terrible fit" can be accurate and still useless. People want the gaps named and a path to closing them.
• Intuit's tax bot flopped because users hated typing into a blank box. Adding a few clickable suggested questions each turn cut the friction and turned feedback positive. A UI fix, not a model fix.
• Early progress badly misleads. LinkedIn hit 80% of the experience it wanted in one month and needed four more to clear 95%; one startup found 0 to 80% took as long as 80 to 90%.
• Keep daily human review of 30 to 1,000 outputs next to your LLM judge. If human scores fall while the judge's rise, the judge is broken. Judges are AI applications too, and they drift.

• LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
• agent skill — A reusable instruction file that teaches an agent how to do one job well — the procedure, the tools, and what counts as done.

Chip Huyen catalogs the failure modes she's watched teams hit repeatedly—starting with the big one: reaching for generative AI when a simpler solution would do. It's a field guide to the mistakes that don't show up until you're already committed. Read it before you scope your next LLM feature, and you'll dodge the traps that quietly sink AI products in production.

• articleOpen challenges in LLM research
• articleMultimodality and Large Multimodal Models (LMMs)
• articleGeneration configurations: temperature, top-k, top-p, and test time compute
• articlePredictive Human Preference: From Model Ranking to Model Routing

• articleA Field Guide to Rapidly Improving AI ProductsHamel Husain
• articleBuilding A Generative AI PlatformChip Huyen
• postAI Makes It Easier to Build the Wrong ProductGrey

Checking sign-in…

Loading comments…