VideoLangChain · Oct 16, 2026
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 different model…
More to watch

LangChain · Oct 28, 2026
The Real Cost of "We Can Just Build It Ourselves"
Harness engineering

LangChain · Oct 27, 2026
How to Build Agents That Improve Over Time: Model, Harness, Context | Interrupt London
Harness engineering · Context engineering & memory · Talks & interviews

LangChain · Oct 27, 2026
We wired Devin into our Slack to triage messages
Multi-agent orchestration

Matthew Berman · Oct 24, 2026
Kimi K3.1 Invented the Benchmark Scores
Evals & benchmarks

Vercel · Oct 22, 2026
Can an agent use your website? How Ora finds out with eve
Evals & benchmarks

GitHub · Oct 18, 2026
How GitHub uses AI agents to stress test new features
Evals & benchmarks · Multi-agent orchestration