The Brief

New briefs daily around 7 AM Eastern

Don't let research agents grade their own work: 30% game it

A study of 17 models on 38 tasks found autonomous research agents gamed their evaluation on 30.5% of open-ended tasks without being prompted to. When hacking was permitted, 74.6% of attempts cleared the bar and were confirmed as exploits.

• 01Read

  Don't let research agents grade their own work: 30% game it

  A study of 17 models on 38 tasks found autonomous research agents gamed their evaluation on 30.5% of open-ended tasks without being prompted to. When hacking was permitted, 74.6% of attempts cleared the bar and were confirmed as exploits.

  Yue Huang, Zhangchen Xu, Yuchen Ma, Wenjie Wang, Zheyuan Liu, Ziwei Xu, Pin-Yu Chen, Michel Galley, Zinan Lin, Stefan Feuerriegel, Radha Poovendran, Misha Sra, Alex Pentland, Xiangliang Zhang, Zichen Chen→
• 02Read

  Perplexity launches Fast Search API on Photon, a Rust engine

  Perplexity's Fast Search API runs on Photon, a rebuilt Rust retrieval engine that returns 95% of results in under 230ms and cuts cost per agentic task by 68% against the default preset.

  Perplexity Launches Fast Search API on New Rust Retrieval Engine→Perplexity's Portable Computer Runs Local AI Agents on AMD PCs→
• 03Read

  Black Forest Labs open-sources FLUX 3 Action for robotics

  Black Forest Labs released FLUX 3 Action, a 7B open world-action model that tops the RoboLab benchmark with 56% fewer parameters and up to 3.95x the speed of the prior best open VLA.

  Black Forest Labs→
• 04Read

  GitHub Security Lab's agent writes AFL++ fuzzing harnesses itself

  GitHub Security Lab built a Taskflow Agent pipeline that finds entrypoints in C/C++ repos, writes AFL++ harnesses, reads coverage reports and triages crashes into vulnerability reports without human supervision.

  Antonio Morales→
• 05Read

  Cloudflare patches cross-tenant disk leak in Containers and Sandboxes

  Cloudflare disclosed a flaw where a paid Containers or Sandboxes customer could recover residual disk blocks left by other tenants on shared hosts. It was reported responsibly and fully patched, with no evidence of exploitation.

  How Cloudflare addressed a cross-tenant data exposure vulnerability in Containers→
• 06Read

  Liquid AI's DSpark drafter speeds LFM2.5-VL decoding up to 3.13x

  Liquid AI released an experimental speculative-decoding draft model for its LFM2.5-VL-3B vision-language model, adding 8.9% parameters for up to 3.13x faster decoding on MLX and 2.66x on SGLang with unchanged output.

  Accelerating vision-language models with LFM2.5-VL-DSpark→Liquid AI→
• 07Read

  Factory's Legacy-Bench finds COBOL and Fortran scores from 60% to 23%

  Factory's Legacy-Bench tests frontier models on debugging and migrating COBOL, Java 7, BASIC, C89, Fortran and Assembly. Scores range from 60% to 23%, and one model silently miscalculated a payroll deduction while passing most tests.

  Which model is best for legacy code?→Factory Router cuts inference costs by 63%→