Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > comp.lang.prolog > #14401

RETRO Project Sebastian Borgeaud et al. - 7 Feb 2022 (Was: Prologers are hurt the most by LLMs)

Show all headers | View raw

Hi,

I posted this already on sci.math, sci.logic and
sci.physics. Its probably the most important addition
to current LLMs, i.e. Retrieval-Augmented Generation (RAG).

But somehow the morons of MSE don't understand a bit
whats going on around and about the world. They are
quite immune to progress in AI. Like stupid cows.

------------------ cut here --------------------

More details on RAG, see here RETRO Project (*) at t=12:01:

What's wrong with LLMs and what we should be building instead
Tom Dietterich - 10.07.2023
https://youtu.be/cEyHsMzbZBs

So its not a very new technique now appearing in
generative AIs on the market as well. Some chat bots
are even now able to sometimes show more clearly the

used source documents in their answer. The MSE end
user can still edit a citation by hand to conform
more to the SEN format, if this would be the issue.

Also the MSE end user can explicitly now ask a chat
bot for sources, which he will get most of the time.
Or he can give a chat bot a source for review and

discussion. This works also. So there is not anymore
this "remoteness" of an LLM to the actual virtual
world of documents. Its more that they now inhabit the

actual virtual world and interact with it. Another issue
I see is that in certain countries and educational
institutions, it might the case that working with a

chat bot is something that the students learn,
yet they are not officially allowed to use it on
MSE, because MSE policies are biased on outdated

views about generative AI.

See also:

(*) RETRO Project:

Improving language models by retrieving from trillions of tokens
Sebastian Borgeaud et al. - 7 Feb 2022
https://arxiv.org/abs/2112.04426

------------------ cut here --------------------

Bye

Mild Shock schrieb:
> Hi,
> 
> Prologers with their pipe dream of Ontologies
> with Axioms are most hurt by LLMs that work
> more on the basis of Fuzzy Logic.
> 
> Even good old "hardmath" is not immune to
> this coping mechanism:
> 
> "I've cast one of my rare votes-to-delete. It is
> a self-answer to the OP's off-topic "question".
> Rather than improve the original post, the effort
> has been made to "promote" some so-called RETRO
> Project by linking YouTube and arxiv.org URLs.
> Not worth retaining IMHO.
> -- hardmath
> 
> https://math.meta.stackexchange.com/a/38051/1482376
> 
> Bye

Back to comp.lang.prolog | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread

Thread

Prologers are hurt the most by LLMs Mild Shock <janburse@fastmail.fm> - 2025-01-10 11:09 +0100
  RETRO Project Sebastian Borgeaud et al. - 7 Feb 2022 (Was: Prologers are hurt the most by LLMs) Mild Shock <janburse@fastmail.fm> - 2025-01-10 11:12 +0100
    SE policy on use of generative Al ignores Retrieval-Augmented Generatio (Was: RETRO Project Sebastian Borgeaud et al. - 7 Feb 2022) Mild Shock <janburse@fastmail.fm> - 2025-01-10 11:15 +0100
      Vectors are the new JSON (Was: SE policy on use of generative Al ignores Retrieval-Augmented Generatio) Mild Shock <janburse@fastmail.fm> - 2025-01-10 11:32 +0100
        XAI is over and out (Was: Vectors are the new JSON) Mild Shock <janburse@fastmail.fm> - 2025-01-10 12:05 +0100
          Academia is retarded (Re: XAI is over and out) Mild Shock <janburse@fastmail.fm> - 2025-01-10 12:21 +0100
  Abstraction Engine / Pattern-Amplification AI Avalanche [Java to C# translation] (Re: Prologers are hurt the most by LLMs) Mild Shock <janburse@fastmail.fm> - 2025-10-04 15:50 +0200
    Swift AI versus Apertus AI: David against Goliath (Re: Abstraction Engine / Pattern-Amplification AI Avalanche [Java to C# translation]) Mild Shock <janburse@fastmail.fm> - 2025-10-04 16:04 +0200

csiph-web