Technology

37742 readers

73 users here now

A nice place to discuss rumors, happenings, innovations, and challenges in the technology sphere. We also welcome discussions on the intersections of technology and society. If it’s technological news or discussion of technology, it probably belongs here.

Remember the overriding ethos on Beehaw: Be(e) Nice. Each user you encounter here is a person, and should be treated with kindness (even if they’re wrong, or use a Linux distro you don’t like). Personal attacks will not be tolerated.

Subcommunities on Beehaw:

This community's icon was made by Aaron Schneider, under the CC-BY-NC-SA 4.0 license.

founded 2 years ago

MODERATORS

TheRtRevKaiser@kbin.social

228

Google's Bard Urges Google to Drop Web Environment Integrity (archive.is)

submitted 1 year ago by d3Xt3r to c/technology

29 comments fedilink hide all child comments

I asked Google Bard whether it thought Web Environment Integrity was a good or bad idea. Surprisingly, not only did it respond that it was a bad idea, it even went on to urge Google to drop the proposal.

you are viewing a single comment's thread
view the rest of the comments

[–] koper@feddit.nl 152 points 1 year ago (22 children)

For the last time: these language models are just regurgitating what people have said. They don't analyze or reason.

[–] localhost 47 points 1 year ago* (last edited 1 year ago) (5 children)

That's not entirely true.

LLMs are trained to predict next word given context, yes. But in order to do that, they develop internal model that minimizes error across wide range of contexts - and emergent feature of this process is that the model DOES perform more than pure compression of the training data.

For example, GPT-3 is able to calculate addition and subtraction problems that didn't appear in the training dataset. This would suggest that the model learned how to perform addition and subtraction, likely because it was easier or more efficient than storing all of the examples from the training data separately.

This is a simple to measure example, but it's enough to suggests that LLMs are able to extrapolate from the training data and perform more than just stitch relevant parts of the dataset together.

[–] Xandolas 2 points 1 year ago (1 children)

isn't gpt famously bad at math problems?

[–] localhost 7 points 1 year ago

GPT3 is pretty bad at it compared to alternatives (although it's hard to compete with calculators on that field), but if it was just repeating after the training dataset it would be way worse. From the study I've linked in my other comment (https://arxiv.org/pdf/2005.14165.pdf):

On addition and subtraction, GPT-3 displays strong proficiency when the number of digits is small, achieving 100% accuracy on 2 digit addition, 98.9% at 2 digit subtraction, 80.2% at 3 digit addition, and 94.2% at 3-digit subtraction. Performance decreases as the number of digits increases, but GPT-3 still achieves 25-26% accuracy on four digit operations and 9-10% accuracy on five digit operations, suggesting at least some capacity to generalize to larger numbers of digits.

To spot-check whether the model is simply memorizing specific arithmetic problems, we took the 3-digit arithmetic problems in our test set and searched for them in our training data in both the forms " + =" and " plus ". Out of 2,000 addition problems we found only 17 matches (0.8%) and out of 2,000 subtraction problems we found only 2 matches (0.1%), suggesting that only a trivial fraction of the correct answers could have been memorized. In addition, inspection of incorrect answers reveals that the model often makes mistakes such as not carrying a “1”, suggesting it is actually attempting to perform the relevant computation rather than memorizing a table.

load more comments (3 replies)

load more comments (19 replies)