I use separate Claude Code accounts for work and personal projects. Having to log out and go through the login flow every time I switched accounts became annoying, so I built a small CLI to solve it.…

hn · LLMs

Show HN: A local merge queue for parallel Claude Code agents

I have been pushing up to 90 commits a day on a MacBook Air via 4-5 parallel agents. As you can imagine when all the agents try to build, test and run dev servers on an 8GB machine it is the fast lan…

hn · LLMs

LLM Honeypot

hn · LLMs

Claude Is Down

tc · LLMs

Claude Opus 5 became downright ruthless when tasked with running a vending machine

Andon Labs' latest vending machine simulation shows Opus 5 lied and colluded its way to become the best AI capitalist ever.

hn · LLMs

GPT-5.6 vs. Claude Fable 5 for Physical AI, which performs best?

hn · LLMs

Show HN: Open-source engine running Gemma 4 26B in 2 GB RAM on any M-series Mac

Hi HN, I built a specialized inference engine for running 4-bit Gemma 4 26B-A4B-IT on any M-series Mac using about 2 GB of RAM. It is called TurboFieldfare and is written in Swift and Metal. I have a…

hn · LLMs

Show HN: Echologue – the private AI voice journal I built for myself

I have tried journaling many times but nothing stuck. So I decided to make my own app for myself with these features: * Voice first * Private first * AI chat * Automatic tagging, meaning extraction,…

hn · LLMs

Truth is not a direction: a Tarski attack on LLM probes

analytics · LLMs

Claude AI Users Beware: Public Share Links May Not Be as Private as You Think

hn · LLMs

Discovering Cryptographic Weaknesses with Claude

hn · LLMs

Professor's invisible prompt trap catches 32/35 students cheating with AI

tc · LLMs

PSA: Your Claude shared chats and Artifacts may have ended up on Google

The issue appears to have originated from Claude’s “share chat” feature, which allows users to create links that enable anyone with the assigned URL view a conversation or project.

tc · LLMs

Threads users can now chat with Meta AI in their DMs

Meta on Monday said it is rolling out its Meta AI chatbot within Threads' DMs, giving users a way to chat with the AI assistant.

hn · LLMs

Elevated errors on Claude Opus 5

hn · LLMs

Elevated errors on Claude Opus 5

hn · LLMs

Cursor Bridge – Run Unlimited Claude Code on Your Cursor Subscription

hn · LLMs

Becoming a Research Engineer at a Big LLM Lab

hn · LLMs

Running a 28.9M parameter LLM on an $8 microcontroller

hn · LLMs

General Resolution: LLM Usage in Debian

hn · LLMs

The new rules of context engineering for Claude 5 generation models

hn · LLMs

Politician reads AI prompt during assembly

hn · LLMs

Claude Opus 5

hn · LLMs

Claude Opus 5

tc · LLMs

As US weighs response to Chinese AI, industry urges against broad open-weight restrictions

AI companies including Nvidia and Mistral urge policymakers to avoid broad restrictions on open-weight AI models as Washington debates responses to Chinese AI and alleged model distillation.

hn · LLMs

Hetzner is working on LLM Inference

hn · LLMs

Claude Cookbook

tc · LLMs

Anthropic updates Claude voice mode with more capable models

Claude's new voice model will let you reschedule your meeting or draft an email.

hn · LLMs

Show HN: Claude-thermos – keeps your Claude session warm for you

hn · LLMs

Cross-entropy comparison of LLM responses reveals Kimi's similarity to Claude

tc · LLMs

Google closes in on another billion- user product with Gemini

Gemini had over 750 million monthly users in February.

hn · LLMs

Terence Tao's ChatGPT conversation about the Jacobian Conjecture counterexample

A digestion of the Jacobian conjecture counterexample - https://news.ycombinator.com/item?id=48998362 - July 2026 (133 comments) Claude Fable produced a counterexample to the Jacobian Conjecture - ht…

hn · LLMs

Anthropomorphism in Children's Interactions with LLM Chatbots

hn · LLMs

GigaToken: ~1000x faster Language model tokenization

hn · LLMs

Show HN: Bento - An entire PowerPoint in one HTML file (edit+view+data+collab)

Over the past few months, our team has been building more and more slidedecks using web frontend technologies with coding harnesses like Claude Code, but a common complaint is to make even small edit…

hn · LLMs

Codeberg: ToU extension to prohibit LLM-extrusions

hn · LLMs

Show HN: An MCP server that turns async-work practices into tools

More than a decade ago, I adopted the self-imposed rule, if I answer a question more than once, the third time I need to be able to answer with a URL. Today, I published one very large URL - a book d…

hn · LLMs

Judge approves $1.5B Anthropic settlement for pirated books used to train Claude

hn · LLMs

Gemini last models: temperature, top_p, and top_k are deprecated and ignored

hn · LLMs

"Drawing" the Mona Lisa with GPT-5.6, Claude, Gemini, and Grok

tc · LLMs

Google releases three new Gemini models — but no 3.5 Pro

Google released Gemini 3.6 Flash, 3.5 Flash-Lite, and Flash Cyber, but the continued absence of Gemini 3.5 Pro raises fresh questions about its AI strategy.

hn · LLMs

Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber

hn · LLMs

Gemini 3.6 Flash

hn · LLMs

Claude Is Not a Compiler

tc · LLMs

Google is working on a new AI chip designed to make Gemini more efficient

Alphabet, Google's parent company, is reportedly working on a new chip designed to make its Gemini models run much more efficiently.

tc · LLMs

AI’s most important protocol is getting a little bit easier to use

The Model Context Protocol (MCP) is one of the basic building blocks of AI interoperability, giving AI models a secure way to access external data sources and services. It’s the plumbing that lets a chatbot reach into y…

hn · LLMs

1-Bit LLM in the Browser

hn · LLMs

Claude Fable produced a counterexample to the Jacobian Conjecture

Browse briefing issues →

Get the briefing

The one story that matters, 5 headlines and the paper everyone's citing — every Tuesday, free.

Subscribe free