Agentic Optimisation: what's fundamentally new for vision in the agent era
_krishna_murthy · x · 2026-09-24
A long-form article, "Agentic Optimisation," argues that many demos framed as "Astra did this" are really agents autonomously calling existing tools, and it's easy to be fooled. The author examines what's fundamentally new for vision in agentic settings, beyond already-solved hard problems.
More from coding & agent
- Treating LLMs as unreliable dependencies: system design for production AI — _jaydeepkarale · 2026-09-24
- ChatGPT over-uses computer use; an AGENTS.md nudge helps a bit — intellectronica · 2026-09-24
- Running pi as a headless harness to auto-process Zoom meetings — JnBrymn · 2026-09-24
- Notch Admits He Enjoys Vibe Coding: 'I May Have Been a Teensy Bit Wrong' — ZeroStateReflex · 2026-09-24
- LangChain adds cron-based schedules so Deep Agents run proactively in the background — Hacubu · 2026-09-24
- GPT-6 feels 'lazy': dev says it's a pair programmer, points to OpenAI model guidance — PaulShellDev · 2026-09-24