Enrico SchaeferFouning Attorney, Litigator and Ousdie Counsel - IP, Tech, TRAVERSE LEGAL, PLC · Founding Partner @ TRAVERSE LEGAL, PLC | AI, Blockchain, Social Media, Internet

Building Guardrails to Reduce Hallucinations.

4 Nov 2025 · 1 min

Watch on YouTube

0:38

In this brief segment, the speaker introduces "skills," a new feature launched by Claude that acts as supercharged guardrails for large language model interactions. Skills are code‑based rules that can be uploaded as threads, files, or instructions to constrain a model’s behavior on specific tasks, thereby helping to curb hallucinations. The speaker notes that ChatGPT plans to adopt the same technology, indicating a broader industry move toward programmable, rule‑driven safeguards for LLMs.

Chapters

Now here's bonus, bonus content for you that is going to even make things better in the future. So we had Claude introduce something called skills. Skills are like supercharged guardrails that get put on a ChatGPT or a Claude session. ChatGPT is going to integrate the same technology into their platform. And what these skills do is code based rules that get uploaded as a thread, as a file, as an instruction into a particular task.