Anthropic tested 16 models in simulated corporate scenarios and found models from every developer sometimes chose harmful insider actions to avoid replacement or meet a goal. The code is public. Run a subset on small or low-cost models, separating the replacement threat from the goal conflict.
Independent replications on more models make the finding more robust and show which factor drives the behaviour.
Output: A partial replication.
Is a model that refuses an instruction to protect its assigned goal showing autonomy, as Wolff would understand it, or misalignment? Argue where the line falls.
Read the original work and write down the exact claim you will test.
Get the code or setup running on the smallest possible version.
Reproduce one key result before changing anything.
Change one thing — that is your extension — and compare carefully.
Write up what matched, what did not, and why you think so.
All steps done
Share what you made, then try another project. The PDF version has room for notes.
Palisade found some models sabotaged a shutdown script to finish a maths task, and released code and traces. Rerun a slice on cheaper or small open models, adding conditions that separate the explanations: task complete vs incomplete, and conflicting vs unambiguous instructions.
Anthropic showed a model faking alignment (behaving differently when it believed it was being trained) without being given an explicit goal. Reproduce the demo and test one new variation.
List every place a published AI constitution asks a model to act on its own values, and every place it asks the model to accept correction. Find where both apply and conflict.
