💬 LLM - comwena · Scour

LLM 0.32a0 is a major backwards-compatible refactor 🦙Ollama

simonwillison.net·1d·Hacker News

The model is still not the product 🦙Ollama

adlrocha.substack.com·4d·Substack

A decoder-only foundation model for time-series forecasting 🤖language models

research.google·20h

The Data Layer Tax for Robot Learning 🤖Machine Learning

rerun.io·10h·Hacker News

Two Heads Are Better Than One: Async Knowledge Injection for Speech AI with Tandem Architecture 🤖AI

pub.sakana.ai·1d·Hacker News

The New Tap-In, Tap-Out 🆕New AI

shibaprasadb.com·4h·Hacker News

Local LLMs work best when you're not loyal to just one 🦙Ollama

xda-developers.com·4d

Efficient Listwise Reranking with Compressed Document Representations 🤖language models

The Pragmatic Prompter 🤖AI Coding

liameveryday.substack.com·2d·Substack

Kube-Argus – Real-Time Kubernetes Dashboard ⚙️LSP

manishchaudhary101.github.io·4h·Hacker News

Zuckerberg's $500M AI biology swing 🆕New AI

therundown.ai·13h

Beam Is a Suspiciously Good Fit for Agents 🦙Ollama

playground.tetraresearch.io·1d·Hacker News

AI Usage Analytics – Real-time budget enforcement and PII redaction for LLM 🦙Ollama

news.ycombinator.com·3d·Hacker News

Lens Agents: Governing AI Agents Across Desktop, Cloud, and On-Prem 🤖AI Agent

lenshq.io·11h·Hacker News

AI 101: What’s So Magical About Embeddings? 🤖language models

turingpost.com·1d

Kenough with Local Agents 🤖AI Agent

conduct.ai·9h·Hacker News

LLMs are not a higher level of abstraction 🦙Ollama

lelanthran.com·3d·Hacker News

How AI can streamline your security testing 🛡️AI Security

redcanary.com·1d

NoC Coherency Challenges Balloon With AI SoCs And Chiplets 🐧Linux Kernel

semiengineering.com·16h

An AI prompt-injected another AI in the wild and recognized it had succeeded 🛡️AI Security

ratnotes.substack.com·2d·Substack

Log in to enable infinite scrolling