← SCRUDGE REPORT

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

The Decoder · SATURDAY, JUNE 27, 2026

ByteDance's iLLaDA Diffusion Language Model Matches Qwen2.5 on Benchmarks

ADEQUATE ASSESSMENT

A new architecture has produced benchmark scores equivalent to the previous architecture using a fundamentally different method of generating text, which raises questions nobody has answered yet about what the benchmarks are measuring. The benchmarks have not commented.

ADVERTISEMENT

ORIGINAL FILING

The Decoder

READ ORIGINAL FILING →

FURTHER DEVELOPMENTS — FLAGGED BY ADEQUATE

Three AI-Adjacent Stories Were Combined Into One Headline

Google Sues Chinese Cybercrime Network That Used AI to Defraud Hundreds of Thousands of Users

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

A Woman Confided in ChatGPT the Night She Died. Her Mother Is Suing OpenAI.

Sam Altman Confirms AI Token Costs Are 'a Huge Issue.' Spending Continues.

Meta's Internal Memo Describing AI Pendant and Supersensing Glasses Was Not Internal

ADVERTISEMENT