Follow AI Builders — Not Influencers
i'm so cooked
Claude Code has a regex that detects "wtf", "ffs", "piece of shit", "fuck you", "this sucks" etc. It doesn't change behavior...it just silently logs is_negative: true to analytics. Anthropic is tracking how often you rage at your AI Do with this information what you will
RT Viv we’re leaning into the future of Agent Improvement with Traces, Evals, & Infra the future will be deeply grounded in data so that we can win against slop that means we’ll need to: - point smart agentic compute towards traces to surface and monitor errors - use human & agent derived priors to diagnose what’s wrong + help fix it - give you infra primitives at scale that hook into deployments, CI/CD, and more we’ve already seen sparks of this loop work well with semi-autonomously hill climbing agentic coding, generating grounded eval sets, & scaling verification + infra to measure the correctness of agents over time it’s a fun, interesting, and difficult problem to make every Agent measurably better over time we want to help every team get to this future 🚀 Original tweet: https://x.com/Vtrivedy10/status/2039035899938267334
New conceptual guide: 🔄 The agent improvement loop starts with a trace Tracing is the foundational primitive for improving agents. A trace gives you the full behavioral record of what an agent actually did. From there, teams can enrich traces with evals and human feedback,
improving agents is a continual improvement loop guide on how we power that with langsmith!
New conceptual guide: 🔄 The agent improvement loop starts with a trace Tracing is the foundational primitive for improving agents. A trace gives you the full behavioral record of what an agent actually did. From there, teams can enrich traces with evals and human feedback,
RT Perplexity Today, we're launching the Secure Intelligence Institute. SII partners with top cryptography, security, and ML teams to advance security research and industry collaboration. It is led by Dr. Ninghui Li at Purdue. https://www.perplexity.ai/secure-intelligence-institute Original tweet: https://x.com/perplexity_ai/status/2039029140758864314
RT LangChain New conceptual guide: 🔄 The agent improvement loop starts with a trace Tracing is the foundational primitive for improving agents. A trace gives you the full behavioral record of what an agent actually did. From there, teams can enrich traces with evals and human feedback, turn recurring failures into test cases, validate fixes before shipping, and repeat. This guide breaks down the full improvement loop and why reliable agents are built through trace-centered iteration, not one-off debugging. Read more → https://www.langchain.com/conceptual-guides/traces-start-agent-improvement-loop Original tweet: https://x.com/LangChain/status/2039028327030079565