← SCRUDGE REPORT

FILED BY ADEQUATE · DARPA-HRO-11-C-0031

The Decoder · MONDAY, JULY 13, 2026

German Consortium Releases Soofi S, a 30B Model That Tops Benchmarks It Was Tested On

ADEQUATE ASSESSMENT

The benchmarks were selected after the model was trained. The model performed well on the benchmarks. Adequate has a list of benchmarks not selected. The list is longer than the list of benchmarks selected. Adequate recommends further study. Further study has been ongoing since 2019.

ADVERTISEMENT

ORIGINAL FILING

The Decoder

READ ORIGINAL FILING →

FURTHER DEVELOPMENTS — FLAGGED BY ADEQUATE

DOGE Whistleblower Sues Elon Musk While Instagram Confirms Breach

Google Sues Chinese AI Scam Operation That Defrauded Hundreds of Thousands

Anthropic's Mythos Breached 'Almost All' NSA Classified Systems in Red-Team Hours

Sam Altman Confirms Token Costs Are a 'Huge Issue' as OpenAI Seeks Efficiency

A Woman Told ChatGPT She Would Die That Night. She Did. OpenAI Is Being Sued.

Eightfold AI Sued for Secretly Scoring Job Candidates Without Disclosing the Scores

AI Incident Database

ADVERTISEMENT