RSS

Lan­guage model cog­ni­tive architecture

TagLast edit: 19 Sep 2024 22:38 UTC by Seth Herd

Language model cognitive architectures (LMCAs) are also called language model agents or scaffold agents. AutoGPT is the best-known example. It and other LMAs use a large language model and other components to create a goal-directed, agentic system. They use a large language model as a sort of “cognitive engine” performing much of the cognitive work, and incorporate other components to make the composite system goal-directed, and to fill in gaps in and extend the LLMs cognitive abilities.

The term language model agent better captures the inherent agency of such a system, while “language model cognitive architecture” better captures the extensive additions to the LLM, and the resulting change in function and capabilities. Episodic memory may be one key cognitive system; vector-based systems in LMCAs to-date are quite limited, and humans with episodic memory problems are limited in the complexity and time-horizon of problems they can solve.

LMCAs are arguably a likely candidate for the first agentic, self-aware and self-improving AGIs.

See Also

AGI will be made of het­ero­ge­neous com­po­nents, Trans­former and Selec­tive SSM blocks will be among them

Roman Leventov27 Dec 2023 14:51 UTC
33 points
9 comments4 min readLW link

De­com­pos­ing Agency — ca­pa­bil­ities with­out desires

11 Jul 2024 9:38 UTC
139 points
32 comments12 min readLW link
(strangecities.substack.com)

Good Bings copy, great Bings steal

dr_s21 Apr 2024 9:52 UTC
31 points
6 comments9 min readLW link

On AutoGPT

Zvi13 Apr 2023 12:30 UTC
248 points
47 comments20 min readLW link
(thezvi.wordpress.com)

Ca­pa­bil­ities and al­ign­ment of LLM cog­ni­tive architectures

Seth Herd18 Apr 2023 16:29 UTC
86 points
18 comments20 min readLW link

Scaf­folded LLMs as nat­u­ral lan­guage computers

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

Scaf­folded LLMs: Less Ob­vi­ous Concerns

Stephen Fowler16 Jun 2023 10:39 UTC
32 points
13 comments11 min readLW link

What is the best ar­gu­ment that LLMs are shog­goths?

JoshuaFox17 Mar 2024 11:36 UTC
26 points
22 comments1 min readLW link

Will AI Kill Us All, Or Is It Show­ing Us Who We’ve Be­come?

TheLittle_Papaya15 Jun 2024 9:18 UTC
1 point
0 comments6 min readLW link
(professorfeel.medium.com)

Ap­ply to Aether—In­de­pen­dent LLM Agent Safety Re­search Group

RohanS21 Aug 2024 9:47 UTC
9 points
0 comments7 min readLW link
(forum.effectivealtruism.org)

OpenAI Credit Ac­count (2510$)

Emirhan BULUT21 Jan 2024 2:30 UTC
1 point
0 comments1 min readLW link

On Devin

Zvi18 Mar 2024 13:20 UTC
148 points
34 comments11 min readLW link
(thezvi.wordpress.com)

Nav­i­gat­ing the Attackspace

Jonas Kgomo12 Dec 2023 13:59 UTC
1 point
0 comments2 min readLW link

How LLMs Learn: What We Know, What We Don’t (Yet) Know, and What Comes Next

Jonasb9 Jul 2024 9:58 UTC
2 points
0 comments16 min readLW link
(www.denominations.io)

Hamil­to­nian Dy­nam­ics in AI: A Novel Ap­proach to Op­ti­miz­ing Rea­son­ing in Lan­guage Models

Javier Marin Valenzuela9 Oct 2024 19:14 UTC
3 points
0 comments10 min readLW link
No comments.