[FRIAM] Swarm again

Marcus Daniels marcus at snoutfarm.com
Sat Nov 9 10:04:24 EST 2024


I think LLMs companies will benefit by developing datasets for reinforcement learning training based on the behavior of modern tools like compilers (and executables), theorem provers, and symbolic math packages.    Some progress can be made with multi-agent conversations and huge context windows, but there needs to be learning – active feedback into the neural net.    I’m not sure when programming will not be a thing.  For me, software development is more about integration and understanding what components are intended to versus what they really do.   But a lot of programmers (or modelers) are write-only type of people.    Writing code or conceptualizing models I think will not be a useful skill in a few years.    LLMs like Claude I think are already better than most people at rationalizing unseen code and suggesting changes.   They need more deep reasoning, though. 

 

From: Friam <friam-bounces at redfish.com> On Behalf Of Pietro Terna
Sent: Saturday, November 9, 2024 6:50 AM
To: friam at redfish.com
Subject: [FRIAM] Swarm again

 

    For people who created http://www.swarm.org or used it, have a look at 
https://github.com/openai/swarm/blob/main/README.md

    Two completely different worlds or a unique one?

    Best, Pietro



-- 
Democrito, che ’l mondo a caso pone (Inferno, IV, 136)
 
"It is the hallmark of any deep truth that its negation is also a deep truth." Niels Bohr.
 
A https://terna.to.it/breviArticoli.html riporto dei miei brevi articoli su temi di attualità.
Asterischi da Verso Itaca a https://verso-itaca.it/asterischi-da-verso-itaca/
 
Home page: https://terna.to.it  Twitter: https://twitter.com/@pietroterna
Mastodon: https://mastodon.uno/@PietroTerna
 
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://redfish.com/pipermail/friam_redfish.com/attachments/20241109/2634b8c8/attachment.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: smime.p7s
Type: application/pkcs7-signature
Size: 5594 bytes
Desc: not available
URL: <http://redfish.com/pipermail/friam_redfish.com/attachments/20241109/2634b8c8/attachment.p7s>


More information about the Friam mailing list