1. Using GPT to Judge GPT Is a Mistake, Here's Why If your agent runs on GPT and your eval judge also runs on GPT, you may be measuring agreement, not quality. Unify CTO Connor Heggie explains why an LLM judge needs to come from a 10/17 03:45 ♡
2. Why Nobody Has Solved Continual Learning Charlie O'Neill, Co-Head of Model Training at Baseten, explains why the train step in the own-your-intelligence loop is still unsolved once you update a model continually instead o 10/16 23:27 ♡
3. Vanta and LangSmith: Assessing Compliance Evidence Like an Auditor "I can finally find the data that I want without having to fight my tooling." Zheng Tao, Senior AI Engineer at Vanta, is building a capability that helps assess compliance evidence 10/16 00:37 ♡
4. How Stripe Built Kai What if everyone had an always-on, production-ready assistant? At Stripe, their answer was a company-wide AI agent called Knowledge AI Platform, also known as Kai. In less than 2 m 10/15 21:25 ♡
5. Why You Think the Frontier Model Is Always Better (It's Psychology) Eno Reyes, CTO of Factory, argues that once people know which model they're using, their preferences fly toward frontier models regardless of actual performance — and that this psy 10/15 21:00 ♡
6. What is Deep Agents? Deep Agents is LangChain's open source agent harness built for long-running tasks. It handles planning, context management, and multi-agent orchestration for complex work like rese 10/14 23:12 ♡
7. What is an Agent Harness? Harness engineering is how we build systems around models to turn them into work engines. A harness is every piece of code, configuration, and execution logic that isn't the model 10/14 03:56 ♡
8. POV: You’re arriving at Interrupt London, The Agent Conference by LangChain. 点击查看该条目的具体内容。 10/13 17:17 ♡
9. Why "best model" is the wrong question now Cognition President Russell Kaplan explains why developer priorities have flipped: once software tasks hit the saturation point where every model can do them well, speed and cost s 10/12 19:30 ♡
10. What is a Skill? Learn what agent skills are and how they help long-running agents manage their own context window. A skill is a folder of instructions, scripts, and reference docs for a specific t 10/10 06:11 ♡
