Axes of Planning in LLMs + Partial Lit Review

·LessWrong··

Epistemic Status: Written over the course of a couple days at Inkhaven. Some of the info is old so some newer papers are excluded.TL;DR: People talk about "interpreting planning and goals" in models all the time, but people have different understandings of what exactly "planning" means. I try to decompose this into a few axes, and categorize some work these ways.We give a model a prompt, it produces and output. How does it work?Do language models Plan?When people look at language models, and wan...

Read full article →

Related Articles

Dirtyfrag: Universal Linux LPE
flipped · Hacker News · 1d ago
A web page that shows you everything the browser told it without asking
mwheelz · Hacker News · 13h ago
DeepSeek 4 Flash local inference engine for Metal
tamnd · Hacker News · 1d ago
An Introduction to Meshtastic
ColinWright · Hacker News · 14h ago
Natural Language Autoencoders: Turning Claude's Thoughts into Text
instagraham · Hacker News · 1d ago