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

Um, these factors were again, they were given significant weight in the in in the tuning.

And as we saw in the early days, psychophancy was an often seen problem.

This arose because you know, we humans reliably prefer being agreed with.

So preference optimization trains models toward agreement, and it takes deliberate.

So, I'm not sure if you're

That's now in place.

We've been able to kind of get that under control.

Another improvement that was impressed upon models was factuality preferring responses that will admit uncertainty rather than always confident fabrication.

Well,

Exactly.

So the other class of behavior that can be trained into a model is its refusal to provide certain classes of information.

That's like that's and what's significant is that there that this exists in two places.

This is different than guardrails.

There's there's filtering what you allow the the you the human prompter to get into.

The model and then filtering what you allow the model to show of its results.

So that's real-time filtering, input and output.

But the but the other place is the you can actually train the model itself to refuse independent of input output filtering.

So, you know.

Which is to say the harn the the harnessing of the model.

Showing 1961–1980 of 17,616 · page 99 of 881