AI Tools & Models HOTFeaturedAll
#LLM

#LLM

50 items · All topics →

Hacker News AI (hnrss)NewScore80

LLMs are terrible at designing AI systems

The author argues that while LLMs write ordinary programs with ease, they often take a roundabout route — building complex symbolic reasoning instead of simply calling another model — when designing systems that use LLMs themselves, and explores possible causes in training data and RL environments.

Nov 17, 14:01

Why this: Covers LLM · Published within 6 hours

Hacker News AI (hnrss)NewScore85

Ask HN: Where are you on the spectrum of AI/LLM adoption?

This Hacker News thread asks developers to place themselves on a scale from autocomplete-only use to fully hands-off agents, and share how far they have actually gone with AI coding.

Nov 17, 13:00

Why this: Covers LLM and Agent · Published within 24 hours

Simon WillisonNewScore80

llm 0.37.3

This is a small bug-fix release, mainly addressing a compatibility issue caused by the newer SQLite shipped with Homebrew.

Nov 17, 07:57

Why this: Covers LLM and release · Published within 24 hours

Ollama ReleasesNewScore80

v0.40.17

The new Ollama release improves ChatGPT CLI restore and graceful restart, and refines details such as OpenCode settings and memory mapping on Vulkan integrated GPUs.

Nov 17, 03:02

Why this: Covers LLM and GPT · Published within 24 hours

arXiv cs.AIScore75

What LLM Agents See and What Users Say

When an agent is about to cancel a booking or delete a file for a user, this paper digs into what actually keeps it from acting on a wrong assumption — the information its tools return, or the user's own words.

Nov 16, 13:00

Why this: Covers LLM and Agent · Relevant to this topic

arXiv cs.AIScore70

Aligning AI Teams

This study explores why alignment training for a single agent often fails to transfer to multi-agent settings, and analyzes the underlying mechanism.

Nov 16, 13:00

Why this: Covers LLM and Agent · Relevant to this topic

arXiv cs.AIScore70

Logically Consistent Accurate Forecasts

This work makes agentic LLM forecasting systems as competitive as expert humans while keeping their forecasts logically consistent.

Nov 16, 13:00

Why this: Covers model and LLM · Relevant to this topic

arXiv cs.AIScore70

Benchmarking AI risk behaviors

This study evaluates LLMs' risk propensity across contexts and task demands, systematically measuring whether models lean risk-averse or risk-tolerant.

Nov 16, 13:00

Why this: Covers model and LLM · Relevant to this topic