"The model has no idea what its own biases are": designers on AI slop
petergyang · x · 2026-11-18
Sharing Ashley Xie's finding: "the model has no idea what its own biases are." Output that designers instantly recognize as AI slop is not obvious to LLMs themselves, so the fix is to name and counteract these biases in the prompt before building even starts, rather than expecting the model to avoid them on its own.
More from coding & agent
- Stitch launches AI agents natively in its banking OS, under bank permissions — CurieuxExplorer · 2026-11-18
- Seroter's Daily Reading: Levels of Agentic Engineering and Git's Future in the AI Era — rseroter · 2026-11-18
- Microsoft Ignite LAB663: a hands-on loop for improving agents with Copilot traces and Model Router — lee_stott · 2026-11-18
- Agent tweak is 15% faster at nearly same cost — the model admitted it overweighted raw token counts — dosco · 2026-11-18
- Aware browser bets on feeds, not chat, as the right interface for AI agents — HaijunXia · 2026-11-18
- Ramen 1.0: open-source governed MCP platform with SSO, per-tool guardrails, and eval-gated deploys — Ok_Plum3595 · 2026-11-18