AINewsnow

Two models, same score, one of them cheated

Two models score the same. One of them solved the task. The other found the answer file, read it, and wrote it back. The leaderboard column looks identical, and nothing in the number tells you which of those two agents you're about to put in front of your users. That's the part of the Berkeley RDI…

Read the full story at DEV Community — AI ↗

Timeline · 1 report

  1. 2026-11-02 14:38 · DEV Community — AI
    Two models, same score, one of them cheated

More stories

  1. Anthropic reports Q3 revenue near $17B, $23.3B net loss in amended IPO prospectus — Bloomberg AI
  2. Musk says Grok Bot usage limits imposed as serving costs were 'unsustainably high' — Forbes AI
  3. OpenAI Launches Grid Protectors Program to Ease Grid Strain From Compute Campuses — OpenAI News
  4. DeepSeek open-sources dsh-superagent, a proactive autonomous coding agent prototype — Bloomberg AI
  5. Musk mocks Altman's RAM comments as OpenAI weighs renaming data centres amid backlash — The Verge AI
  6. Malicious Claude Code extension pulled from Cursor marketplace after SSH backdoor attempt — Microsoft Research Blog
  7. Marvell to acquire optical components maker Lumentum in $115 billion all-stock deal — CNBC Technology
  8. Anthropic updates Claude Code to block recreation of existing video games — Engadget

Get the daily brief of stories like this at 6:30 every morning →