Quick LLM writing fix: make it motivate claims, says ex-OpenAI researcher
ChowdhuryNeil · x · 2026-11-22
Neil Chowdhury shares a low-hanging fruit for better scientific writing with LLMs: ask the model to motivate what it's saying. LLMs assume too much of the reader by default, which is one reason AI-written prose often feels illegible.
More from Apps
- Delta quietly removes phone call-back option, likely due to AI agents — MatthewChang · 2026-11-22
- Dev builds Beam, an open-source local AirDrop: scan a QR, no apps, Wi-Fi-only file transfer — saheedniyi_02 · 2026-11-22
- Indie dev upgrades InstantFamilyPhoto, his first app that ever sold — tristanbob · 2026-11-22
- Claude can now design print-ready holiday cards — 7 prompts to replace Canva — aftahi_ai · 2026-11-22
- AWS Quick, Amazon's free AI office assistant, offers 10 hours monthly per user — lxfater · 2026-11-22
- Musk amplifies Tesla FSD V15 feature letting drivers pick any parking spot — elonmusk · 2026-11-22