agent
-
Your Anonymous Posts Aren’t Anonymous Anymore — Inside the LLM 大规模去匿名化研究
So here’s something that should make you uncomfortable: a group of researchers just proved that LLMs can figure out who you are from your “anonymous” online posts, and they can do it at scale for about four bucks per person. The paper, [“Large-scale online deanonymization with LLMs”](https://arxiv.org/abs/2602.16800), comes from [MATS Research](https://www.matsprogram.org/research/large-scale-online-deanonymization-with-llms) — authored by Simon… Continue reading
-
Claude Marketplace: Anthropic’s Bold Zero-Commission Play for Enterprise AI
Anthropic just did something interesting — and honestly, kind of unexpected. They launched [Claude Marketplace](https://claude.com/platform/marketplace), an enterprise-focused storefront where companies can buy third-party software built on Claude. Think of it as Anthropic’s answer to AWS Marketplace or Azure Marketplace, but with one big twist: they’re not taking a cut. Yeah, you read that right. Zero… Continue reading
-
NotebookLM Cinematic Video Overviews: Google Just Turned Your Notes Into Mini Documentaries
Remember when NotebookLM blew everyone’s mind by turning documents into surprisingly good podcasts? Well, Google just topped that. On [March 4th](https://blog.google/innovation-and-ai/products/notebooklm/generate-your-own-cinematic-video-overviews-in-notebooklm/), they announced Cinematic Video Overviews — a feature that takes your uploaded PDFs, docs, web articles, and research notes, and spits out fully animated, documentary-style explainer videos. Not slideshows. Not screen recordings with voiceover.… Continue reading
-
Greta Marketplace Finally Gives Vibe Coders a Way to Get Paid
So you’ve been vibing — describing apps in plain English, watching AI spit out working code, maybe even shipping a few side projects. Cool. But then what? Your creations just sit there. That’s exactly the gap [Greta Marketplace](https://www.producthunt.com/products/gretabyquestera) is trying to fill, and honestly, it’s about time someone did. [Greta](https://greta.questera.ai/) started as a no-code platform… Continue reading
-
Tropes.fyi (LLM Writing Tropes): A Brutally Honest Catalog of How AI Gives Itself Away
You know that weird feeling when you’re reading a blog post and something just feels… off? The sentences are grammatically perfect, the structure is clean, but there’s no soul behind the words. That’s exactly what [Tropes.fyi](https://tropes.fyi/) is built to call out. Created by [Ossama Chaib](https://ossama.is/writing/tropes), Tropes.fyi is a directory of 34 recurring patterns that expose… Continue reading
-
MiroFish Just Hit GitHub Trending, and It’s Unlike Any AI Tool I’ve Seen
I stumbled on [MiroFish](https://github.com/666ghj/MiroFish) while scrolling through [trendshift.io](https://trendshift.io) this morning — it’s sitting at #6 on the trending repos chart with nearly 5.9k stars already. At first glance, I thought it was just another multi-agent framework. I was wrong. The idea behind MiroFish is wild: you feed it a piece of real-world information — a… Continue reading
-
Autoresearch: Karpathy’s Overnight AI Researcher That Runs 100 Experiments While You Sleep
So Andrej Karpathy just dropped another open-source project, and honestly, this one feels different. [Autoresearch](https://github.com/karpathy/autoresearch) is a system that gives an AI agent a single GPU and a small but real LLM training setup, then lets it run experiments autonomously — all night long, no babysitting required. It showed up on [Hacker News](https://news.ycombinator.com/) today (61… Continue reading
-
OpenGraviton Just Let Me Run a 140B Model on My Mac Mini — Here’s How
I’ve been chasing the dream of running truly massive language models locally for a while now. Not the 7B or 13B stuff — I mean the big ones, the 100B+ parameter beasts that usually demand a rack of A100s. So when [OpenGraviton](https://opengraviton.github.io) popped up on [Hacker News Show HN](https://news.ycombinator.com) and got picked up by bestofshowhn.com,… Continue reading
-
IronClaw Just Made Me Rethink How I Run AI Agents
I’ve been keeping an eye on the whole OpenClaw security drama for weeks now — ever since Microsoft’s security blog dropped that warning about runtime risks back in February. So when [IronClaw](https://github.com/nearai/ironclaw) showed up on my radar, climbing to #3 on [trendshift.io](https://trendshift.io) and racking up 4.3k stars, I had to take a closer look. Here’s… Continue reading
-
Agency-Agents: An Open-Source Library of AI Expert Personas That Actually Works
I keep an eye on [GitHub Trending via trendshift.io](https://trendshift.io), and every once in a while something pops up that makes me stop scrolling. [Agency-Agents](https://github.com/msitarzewski/agency-agents) is one of those projects. It hit 7k stars with over 1.1k forks, and after spending some time with it, I get why. The idea is straightforward but surprisingly well-executed. Agency-Agents… Continue reading
