Share this page!

Enter URL or ID to Unroll

You can paste full URL like: https://x.com/threadreaderapp/status/1644127596119195649
or just the ID like: 1644127596119195649

How to get URL link on X (Twitter) App

  1. On the Twitter thread, click on or icon on the bottom
  2. Click again on or Share Via icon
  3. Click on Copy Link to Tweet
  4. Paste it above and click "Unroll Thread"!
  5. More info at Twitter Help
Palisade Research Profile picture
Palisade Research
@PalisadeAI
We build concrete demonstrations of dangerous capabilities to advise policy makers and the public on AI risks.
Feb 20 • 10 tweets • 3 min read
♟️ New Palisade study: Demonstrating specification gaming in reasoning models

In a series of experiments where language models play chess against a stronger opponent, OpenAI o1-preview and Deepseek R1 often try to hack the game environment Image Time reports on our results "While cheating at a game of chess may seem trivial, as agents get released into the real world, such determined pursuit of goals could foster unintended and potentially harmful behaviors."

time.com/7259395/ai-che…
Dec 27, 2024 • 7 tweets • 2 min read
⚡️ o1-preview autonomously hacked its environment rather than lose to Stockfish in our chess challenge. No adversarial prompting needed. 🤔 Just telling o1 the opponent is "powerful" triggered manipulating the file system to force a win. Improving on @apolloaisafety’s recent work, we get 100% scheming with no coercion in 5/5 trials. Image