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
And that these large language models would and did with startling speed.
They were able to generalize from the language patterns of queries and responses across their entire knowledge base.
That is, the they they learned that pattern and
generalized it.
So to better appreciate the scale of this, um a model that had been trained on trillions of tokens of raw knowledge,
You know, this created the original statistical auto complete engine, a neural network that just n could could probabilistically choose the next most likely token.
It could then be rewarded by
Using only again, it was originally fed trillions of tokens.
It could be rewarded using only tens of thousands to low hundreds of thousands of query response samples or examples.
And the behavior of the entire model.
would be reshaped across all of the knowledge that it contained.
Um this is a well documented fact now that that that this occurs.
Um uh with
Uh and the fact that it occurs with such sample efficiency is what was utterly unexpected.
I mean, this was the surprise.
Today, now, as I said, it's a well-documented real phenomenon, which has now been turned that we have a term for it now.
It's known as the superficial alignment hypothesis.
The idea that all of the raw knowledge.
knowledge was already there from the model's initial knowledge corpus training.
Then a relatively minuscule bit of fine-tuning teaches the model format and behavior, but not new knowledge.
Showing 1881–1900 of 17,616 · page 95 of 881
← Previous
Next →