Make visuals for your AI workflow: model-to-human bitrate is the real bottleneck
vtabbott_ · x · 2026-09-16
vtabbott shares a workflow tip: strongly recommends creating visuals for whatever you're working on with AI.
Key points:
- The model-to-human bitrate is a major workflow bottleneck, and humans have a very strong visual reasoning stack that should be put to use
- Following up on details, he adds that what matters is competence + reliability: the system must not make mistakes, not make a mess, and parse instructions well. In his view Opus doesn't quite make the cut, and Google's Astra is "VERY spikey"
- He's curious how others' experiences compare
More from coding & agent
- When an LLM plans an executable agent DAG, where do you draw the trust boundary? — Repulsive_Sugar_5252 · 2026-09-16
- "Never again": user rants Nemotron 3 Ultra can't find .github and stalls for 90 minutes — dwerps · 2026-09-16
- Personal AI's real test: does your judgment survive after you close the window? — sujingshen · 2026-09-16
- Coding agent so fears AWS costs it wrote a test banning NAT gateways — mimi10v3 · 2026-09-16
- Muse Code raises contributor tier limits and resets usage for all subscribers — giffmana · 2026-09-16
- OpenAI reportedly orchestrates 10k internal agents without quality loss, while users' sub-agents 'just burn tokens' — RexDouglass · 2026-09-16