🦞🌯 Lobster Roll

All LHN/.~Ars
RSS

Showing stories from 2025-06. View all

NewestOldestTop ScoredMost Discussed
Importance of context management in AI NPCs (walterfreedom.com)
Show HN: Local LLM Notepad – run a GPT-style model from a USB stick (github.com)
What it is A single 45 MB Windows .exe that embeds llama.cpp and a minimal Tk UI. Copy it (plus any .gguf model) to a flash drive, double-click on any Windows PC, and you’re chatting with an LLM—no admin rights, Cloud, or network.<p>Why I built it Existing “local LLM” GUIs assume you can pip install...
AI that answers questions without making you hate the internet
I just wanted to ask Google how to stop overthinking.<p>Instead, I got SEO clickbait, Pinterest affirmations, and a YouTube video of a dude whispering over lo-fi beats.<p>So I built Nexix: an emotionally unavailable AI that just gives you the answer — no influencers, no ads, no “Top 10 Mindfulness R...
Ask HN: Which skill do you believe will take the longest to be replaced by AI?
There is a lot of debate whether AI will surpass humans in all economically viable skills (AGI, by one definition). Regardless of whether this will happen, or when, many people already have lost their jobs in part due to the emerging capabilities of AI models, including writing, document analysis, d...
AI is Anti-Human (and assorted qualifications) (njump.me)
SiliconFlow, one-stop AI platform for inference, fine-tune and custom deployment (siliconflow.com)
GPEmu: A GPU emulator for rapid, low-cost deep learning prototyping [pdf] (vldb.org)
The race to make AI as multilingual as Europe (thenextweb.com)
So It Begins Is This a Real Band or AI? [video] (youtube.com)
MCP to .dxt Command for Claude Code (claudecodecommands.directory)
Researchers Uncover Hidden Ingredients Behind AI Creativity (quantamagazine.org)
The AI-Native Airtable Has Arrived: A Letter from Our CEO (airtable.com)
Why Generalists Will Lead in the Age of AI (opuslabs.substack.com)
Transformers Are Graph Neural Networks (arxiv.org)
How AI on Microcontrollers Works: Operators and Kernels (danielmangum.com)
AMD bets on rack-scale compute to boost AI efficiency 20x by 2030 (theregister.com)
GPT4Free: "educational project" for free LLM inference from various services (github.com)
Embodied AI Agents: Modeling the World (arxiv.org)
Show HN: C.O.R.E – Opensource, user owned, shareable memory for Claude, Cursor (github.com)
Hi HN,<p>I keep running in the same problem of each AI app “remembers” me in its own silo. ChatGPT knows my project details, Cursor forgets them, Claude starts from zero… so I end up re-explaining myself dozens of times a day across these apps.<p>The deeper problem<p>1. Not portable – context is ven...
ChatGPT intercepts clear cache keyboard shortcut in Brave
And probably other Chromium based browsers. Why is this even possible and does not represent huge security vulnerability?
LLVM: InstCombine: A PR by Alex Gaynor and Claude Code (simonwillison.net)
llvm: InstCombine: improve optimizations for ceiling division with no overflow—a PR by Alex Gaynor and Claude Code (simonwillison.net)
Connected Gmail mcp to AI voice (harmony.com.ai)
Exploring LLM Evaluation by Using Games (lmgame.org)
Eigenvalues of Generative Media (stackdiver.com)
The new skill in AI is not prompting, it's context engineering (philschmid.de)
Symbients on Stage Coming Soon: Autonomous AI Entrepreneurs (forbes.com)
Can Large Language Models Help Students Prove Software Correctness? (arxiv.org)
Developing with GitHub Copilot Agent Mode and MCP (austen.info)
Large Language Model-Powered Agent for C to Rust Code Translation (arxiv.org)