zlatkov

↗ HN profile [ 76.1 ms ] full profile

No user record in our sample, but zlatkov has activity below (stories or comments). Likely we have partial data — the full bulk-load will fill profiles in.

  1. Hi HN! We’re the team behind Fiddler, and we recently built an Agent Cache feature. It works by capturing an LLM request/response pair and, once caching is enabled, serving subsequent matching calls locally so duplicate…

  2. Question for anyone using OpenClaw (or similar) agents daily. I've been writing new skills for my OpenClaw setup and keep running into the same thing: strong models (like Opus 4.6) do great even with complex skills, but…

  3. https://openai.com/index/scaling-ai-for-everyone/ https://x.com/sama/status/2027386252555919386 https://xcancel.com/sama/status/2027386252555919386

  4. Every agent run (and especially when running tests in CI/CD) adds token cost, nondeterminism, and slows iteration. I’m not talking about LLM evals here. I mean integration-style testing. There are some workarounds like…

  5. Hi HN - I’m Alex, currently Head of Agent Development Tools at Progress. Before this, I was a Co-founder/CEO of a session replay startup called SessionStack, which was acquired in August this year. Since then, I’ve been…

  6. How to Build a CLI with JavaScript (blog.sessionstack.com)
  7. How JavaScript Works: Recursion (blog.sessionstack.com)