oleczek

Fair point - I overstated it. Thanks for the correction.

Thanks for vouching. Appreciate the heads-up.

Yeah, original is clearer. Just went with the shorter one so more people would actually click.

yeah English isn't my first language so i used AI to clean up the writing. the research, the data and the analysis are all mine and all open (in the linked repo)

Yeah, the optimism/hedging part lines up nicely with that framing. The bit that still puzzles me is that the same edit moved expressed confidence in opposite directions — down for Gemma, up for Qwen. If it were simply removing one shared "anxiety" factor, I’d have expected the sign to stay consistent. So whatever caution is doing here seems a bit more tangled up with each model’s own disposition than a single clean knob.

Author here. Quick version: “abliteration” (basically removing the direction in the model that causes it to refuse) is the go-to method people use to make open models uncensored.

Most people treat it like a clean surgical cut - it just kills the refusals and leaves everything else untouched. I tested that assumption on Gemma and Qwen with 21,600 pre-registered decisions under uncertainty, using identical frozen inputs for the base vs. abliterated versions.

Turns out it’s not surgical at all.

The abliterated models systematically become more optimistic, hedge less, show no improvement in actual task performance, and the same edit even moves their expressed confidence in opposite directions depending on the model family.

Preregistration, dataset, and analysis code are all public. Happy to answer any methodology questions or hear where you think this falls apart.