A request logger can demystify LLM harnesses
mattpocockuk · x · 2026-07-20
Matt Pocock says one of the strongest parts of his upcoming course is a request logger that lets learners inspect the raw payloads sent to Anthropic/OpenAI.
He says this has three practical benefits:
- It makes the mechanics obvious: sessions, context windows, and the boundary between the model and the harness.
- It creates context paranoia by showing that every token matters and waste is easy to spot.
- It encourages people to build their own harnesses, because the “magic” disappears once you see the actual requests.
The point is less about a single trick and more about teaching how LLM workflows really work under the hood.
More from coding & agent
- Reticle builds a verification layer that lets AI coding agents check their own generated code — Scobleizer · 2026-10-27
- Trust your agent, but read its logs: Claude managed agents tips — brada · 2026-10-27
- Dev training a guard model to block prompt injection, tool and memory poisoning — gnukeith · 2026-10-27
- Dev trains a ~4GB-VRAM sentinel model to guard against prompt injection and poisoned memory — gnukeith · 2026-10-27
- Superset rebrands as Paradev, raises $11.5M seed led by USV — massimosgrelli · 2026-10-27
- Ex-Big Tech managers may thrive in the AI era: manage agents like you managed teams — lxfater · 2026-10-27