• Search
  • Topics
  • Nodes
< back

#llms

16 109 Toot LinkedIn
A chart of hourly posts over the last week (for big screens). A chart of hourly posts over the last week (for small screens).

1

From arxiv.org

Clarifying Before Reasoning: A Coq Prover with Structural Context

1 2

In this work, we investigate whether improving task clarity can enhance reasoning ability of large language models, focusing on theorem proving in Coq. We introduce a concept-level metric to evaluate task clarity and show that adding structured semantic context to the standard input used by...

#itp #llms #coqprover

on Fri, 10AM


1

From arxiv.org

Bourbaki: Self-Generated and Goal-Conditioned MDPs for Theorem Proving

1 2

Reasoning remains a challenging task for large language models (LLMs), especially within the logically constrained environment of automated theorem proving (ATP), due to sparse rewards and the vast scale of proofs. These challenges are amplified in benchmarks like PutnamBench, which contains...

#itp #llms #leanprover

on Fri, 10AM


1

From substack.com

The Dumbest Move in Tech Right Now: Laying Off Developers Because of AI

1 1

AI-assisted coding doesn’t mean fewer developers—it means more ambitious, higher-quality products

#ai #llms #genai #solidstatelife #technologicalunemployment

on May 19


1

From blogspot.com

A non-anthropomorphized view of LLMs

3 28

In many discussions where questions of "alignment" or "AI safety" crop up, I am baffled by seriously intelligent people imbuing almost magic...

#llm #llms

on Sun, 9PM


1

From 404media.co

Researchers Jailbreak AI by Flooding It With Bullshit Jargon

19 19

LLMs don’t read the danger in requests if you use enough big words.

#llms #ai

6h ago


1

From arstechnica.com

How a big shift in training LLMs led to a capability explosion

2 8

Reinforcement learning, explained with a minimum of math and jargon.

#llms #arstechnica #reinforcementlearning

on Mon, 11AM


1

From simonwillison.net

Become a command-line superhero with Simon Willison’s llm tool

1 1

Christopher Smith ran a mini hackathon in Albany New York at the weekend around uses of my LLM - the first in-person event I'm aware of dedicated to that project! …

#ai #llm #llms #openrouter #generativeai

14h ago

Showing first 9 out of 10