RSS

AI “Agent” Scaffolds

TagLast edit: 24 Mar 2025 19:03 UTC by Raemon

AI “Agent” Scaffolds take an AI such as an LLM, and build structure around it to allow to accomplish more complex goals. (These are generally referred to as “AI agents”, although typically aren’t full “agents” in the sense that traditional LW writing was focused on, i.e. they don’t obviously have goals of their own that they are pursuing)

An­a­lyz­ing long agent tran­scripts (Do­cent)

jsteinhardt24 Mar 2025 20:49 UTC
41 points
2 comments1 min readLW link
(bounded-regret.ghost.io)

What is scaf­fold­ing?

27 Mar 2025 9:06 UTC
10 points
0 comments2 min readLW link
(aisafety.info)

How dan­ger­ous is en­coded rea­son­ing?

artkpv30 Jun 2025 11:54 UTC
17 points
0 comments10 min readLW link

End-to-end hack­ing with lan­guage models

tchauvin5 Apr 2024 15:06 UTC
29 points
0 comments8 min readLW link

Creat­ing un­re­stricted AI Agents with Com­mand R+

Simon Lermen16 Apr 2024 14:52 UTC
77 points
13 comments5 min readLW link

De­liber­a­tive Cog­ni­tive Al­gorithms as Scaffolding

Cole Wyeth23 Feb 2024 17:15 UTC
20 points
4 comments3 min readLW link

Scaf­folded LLMs: Less Ob­vi­ous Concerns

Stephen Fowler16 Jun 2023 10:39 UTC
34 points
15 comments14 min readLW link

Scaf­folded LLMs as nat­u­ral lan­guage computers

beren12 Apr 2023 10:47 UTC
95 points
10 comments11 min readLW link

Chang­ing times need new Change man­age­ment ide­olo­gies: High­light­ing the need for up­grade in Change man­age­ment of fu­ture agen­tic workforces

Aiphilosopher15 Jul 2025 10:49 UTC
1 point
0 comments1 min readLW link
No comments.