Steve Gibson

speaker

17,616 appearances 14 recordings 1 series first heard May 2026 last heard 2 Sep

Steve Gibson’s voice in public audio — every appearance, attributed to the second.

Trend

recordings per month · last 12 months

Recordings per month over the last 12 months — 14 in all, peaking in Jul 2026 with 5.

Appearances

newest first · ▶ plays the moment

Security Now (Audio) · SN 1092: Restraint Abliteration - Rotating Keys, Broken Guardrails · 19 Aug 2026 podcast

Refusal behavior is mediated by a specific direction in the model's residual stream.

If we prevent the model from representing this direction, it loses its ability to refuse requests.

That our Diddy reference, as I said, is the research I referred to previously, which showed the world how to do this, just how to simply perform this excision.

Uh, the blog posting on Hugging Face is one artifact of that preceding research, and the companion repository on GitHub contains all of the details.

Uh that that is uh it i it's m-l-a-b-o-n-n-e dot github.io um and it is uh uncensor any lm with obliteration.

So and as you would expect, it was all tremendously exciting to the world's AI hackers, many of whom immediately jumped on uh any and every

Every published and available open weight model and happily obliterated away any and all perceived and imposed censorship upon those models.

And those obliterated public open weight models are now available for use by anyone who can harness them.

And as you said, Leo, you've seen them both with and without the

uh the the uh censorship uh obliterated from them.

This

Finally brings us to the first major topic I wanted to discuss today.

Now that we have a much deeper understanding of where these chatbots came from, how they work, how they can have behavior imprinted upon them after they've been filled with raw not with raw knowledge, and how unfortunately brittle that imprinting is.

So, okay, now I I also need to mention that the term pre-training is what the AI industry has unfortunately landed on to actually mean training, uh, the training that occurs before the post-training.

And I suppose since there is now always going to be a definite post-training phase during which the behavior is layered on top of the previously trained in knowledge, you know, it if if if that pre-training were just called training, which is actually what it is, then it might be assumed to encompass both the training.

training and the post-training, meaning if it was just called training, that would it would mean all training.

So my point is there's pre-training and there's post-training and there is not any just training in the middle.

We don't have we we we don't use that.

Showing 2121–2140 of 17,616 · page 107 of 881