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
They said we we tested gram in three settings of increasing realism.
First, on a synthetic data set of children's stories tagged by topic, a small gram model could be reconfigured to forget any chosen topic.
And each configuration performed almost identically to
A separate model trained from scratch with that topic filtered out.
In other words, they did an A-B comparison.
Here's a gram, gram-trained model where we turned off the topic, comparing it to a normal model that was never trained with that topic, and there's no difference in uh in in behavior.
They said, um and and and they they made it more clear, they said that is for the cost of training a single model, we achieved results that would normally require multiple training runs on different data sets.
Second, we trained a larger model on a realistic mixed uh mix of web text code and scientific papers with four dual use domains virology, cybersecurity, nuclear physics, and a niche programming language just to serve as a proxy for specialized dual use code.
They said the capability associated with each dual use domain is routed to its own module.
Deleting a module removed the corresponding capability about as effectively as never having trained on that data at all.
Remarkably, they said, we find that this removal did not degrade general performance.
Performance.
And finally, they said we also tested whether an attacker could recover the removed knowledge by training on a small amount of malicious data.
Believe it or not, Graham resisted this about as well as data filtering did.
By contrast, an unlearning technique applied after training only suppressed.
The knowledge.
That's what we've been talking about.
It was easy to remove that with a small amount of fine-tuning.
So that so that that's a parenthetical about the um the resistance ablation.
And then finally, third, they said, we ran the experiment at seven model sizes from 50 million to 5 billion parameters.
Showing 2281–2300 of 17,616 · page 115 of 881
← Previous
Next →