FutureHouse's deslopper trains Kosmos to write indistinguishably from human experts
proteinrosh · x · 2026-11-12
The FutureHouse team got tired of AI slop, so they built a "deslopper" that lets their research agent Kosmos teach itself to write like a human expert in any domain. They claim experts can no longer distinguish the model outputs from real human-written text, and released side-by-side examples.
A recipient confirms a Kosmos-generated report was far more readable than most AI text.
More from Models
- Google launches Gemini Decisions API: 1,000 evals per request at $0 output cost — DynamicWebPaige · 2026-11-12
- OpenAI's five biggest failures laid out: pretraining decline, alignment fears, enterprise lost to Claude — teortaxesTex · 2026-11-12
- Fable 5.2 Hits 41.3% on Remote Labor Index, Up From 2.5% a Year Ago — alliekmiller · 2026-11-12
- Beaker automates MIT's weight-space programming: one-neuron edit lifts MATH-500 from 7% to 37% for under $4 — VictorSanh · 2026-11-12
- Researcher says Anthropic dodged questions on Mythos false positive rate; 37,966 findings, 2 exploited — OwariDa · 2026-11-12
- Grok spotted building meeting "Listen to Conversation" feature with live transcript — nima_owji · 2026-11-12