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
It did the knowledge was would have never been put in there.
So it's just not there to ask.
But it you you would you would spend so much money training that up.
And this is the problem that that they're trying to identify.
So
The quite valid point that Anthropic is making here is that it's massively infeasible to train a state-of-the-art model on any pre-filtered knowledge to make it dumb about some things.
I don't know anything about that.
You know, if you're going to be spending that kind of money on training, it needs to know everything so that it can have the
widest application range for its use, you know, in order to have some chance of getting some money back out of all that training that went into it.
So if a state-of-the-art model were to be trained on a filtered subset of everything, then uh, you know, that is it a a a limited one forever, you end up with a very expensive
forever limited model.
Um
Okay, so
Um
We've seen that imposing post-training behavior, which is what we're just talking about, this refusal obliteration, post-training behavioral net r restrictions on open source models, where you're able to modify the network weights.
That can be altered.
So it was a short-lived solution.
Um, the means for removing those restrictions, as we saw, so it's all public knowledge, child's play, you know, and even the best closed-weight models, which are operated by cloud-based hyperscalers, you know, like OpenAI, Anthropic, and Google and so forth, AWS.
Um, we've seen that they can be pro.
To trickery and abuse.
Showing 2201–2220 of 17,616 · page 111 of 881
← Previous
Next →