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 monthsRecordings per month over the last 12 months — 14 in all, peaking in Jul 2026 with 5.
Appearances
Um, we've, you know, prompt injection example, and we're next week we're going to understand exactly how that happens.
So what's clearly needed is a new solution.
And that's what these researchers have found.
Um, Leo, we're at two hours.
Let's take our last break and then we're gonna look at the solution for this dual use problem and how to how to solve this with a single training.
And and again, as a user, you'd I mean oh Lori, she's using the doesn't matter, yeah, neck out of uh chat GPT, but our audience, that's why they're here.
Sure.
Is to get this.
So um because
Post training.
uh behavior modification has been demonstrated to be easily removable.
It is not sufficient to say don't don't give people these uh you know disinformation.
Uh uh it doesn't work to suppress that behavior.
What we need is a new solution.
And it's completely infeasible to do multiple training runs
With different combinations of information filtered out of a model because training is prohibitively expensive.
So what we need is a new solution.
And that's what these researchers working with Anthropic have found.
Anthropic continues their writing saying, in new research carried out with collaborators at AE Studio, we explore a new method.
that could enable the benefits of training many separately filtered models, but at the cost of training only one.
Showing 2221–2240 of 17,616 · page 112 of 881
← Previous
Next →