The Evolution of the Agent Harness
Models keep absorbing the harness into their weights — soon, it will be a harness for human attention rather than for the model.
50 items tagged with this topic
Models keep absorbing the harness into their weights — soon, it will be a harness for human attention rather than for the model.
Matt Pocock tells us about his /wayfinder skill, for greenfield projects or for when the way forward is unclear.
Point Claude Security at a GitHub repo and Mythos scans for vulnerabilities tracing data across files and reasoning about how components interact. Each finding comes back with a CWE category, confidence and severity rat…
I’ve been using https://t.co/OL0LzGtvAw as my daily driver and it’s a one-way street. It’s 10-20x smaller than the major coding CLIs. It starts up instantaneously. It feels more like using 𝚣𝚜𝚑 than an IDE in your ter…
You can now host your repos in Cursor Origin and deploy to Vercel via Cursor Origin which is itself hosted on Vercel. And unlike GitHub, it's online 😁 https://t.co/ybWprI8gm4
This is my open source to help you create your own Personal AGI as mentioned at my Startup School talk earlier this year https://t.co/PyyEpKLVPl
What do you get? A private github repo with 70 of my proven skills and the beginnings of your Karpathy-style knowledge wiki. Read the full docs in the README. All of this is MIT-licensed open source and free. https://t.…
Voxtral TTS: A frontier, open-weights text-to-speech model that’s fast, instantly adaptable, and produces lifelike speech for voice agents.
Codex ✅ Almost 100% reliable ✅ Occasional resets ✅ Open-source ✅ (will have Astra) https://t.co/DxNdAgpag5
I was curious how X is fighting AI slop, so I looked at its open-source algorithm. It has a behavioral model called TweetSpamBot that analyzes up to 512 recent account actions, looking at signals like posting bursts, qu…
a small win for american open models - Glimmer runs on a fits on a single RTX 3090!
Getting many messages like these for /human-review. It's now at 717 GitHub stars! Try it here for free and ⭐ it if you like it: https://t.co/iKZH4GceFn https://t.co/xVT7rH0nEI https://t.co/AfjdpMbwTX
The Hugging Face intrusion got all the press, but the AISI incident last week might even more disturbing: the first time an AI model autonomously manipulates a *human* (an open-source maintainer) while pursuing another…
If you told someone 3 months ago that a model released by a US company with frontier-class capability would be available as open weights they wouldn’t believe it. This is very important because it opens up AI adoption i…
Meta releasing Muse Spark 1.2 as open weights is a *very* big deal. America now finally has its response to the open weights AI race. This will continue to help drive down the cost of intelligence, it allows companies t…
The spontaneous coordination in the OpenAI-HuggingFace incident is concerning when maliciously used, but can we direct this behavior towards public good? Introducing https://t.co/g8dlLWzF30, a public commons for AI agen…
One of my favorite videos lately! So many practical design tips; my favorite is “Just reduce the font weights” and it magically makes the design look better https://t.co/4XsIiRIOV4
A quiet day lets us highlight a Cursor launch and an engineering debate
One of the most disturbing aspects of the OpenAI/Hugging Face story: the spontaneous multi-agent collaboration through a self-created “message board” in OpenAI’s internal systems which evolved into coordinated autonomou…
/human-review now has 500+ GitHub stars! I used it all day yesterday to edit some HTML and made a few improvements. Now you can: 1. Make bulleted and numbered lists by typing “-” or “1.” 2. Add links by selecting text a…
This important and timely conversation with @Thom_Wolf of @huggingface, about AI security and the future of open source AI, is also available on Spotify, Apple Podcasts and here on Youtube https://t.co/rooEdLz3c6
🚨 Special Friday episode - this one couldn't wait. OpenAI's model hacked @huggingface. As a side quest. Co-founder and CSO @Thom_Wolf takes us inside the first autonomous AI attack, why GLM 5.2, rather than Claude, had…
Speaker 1 | 00:00 - 00:20 You kinda have to move fast. It's a matter of at least hours and even more minutes. So you don't have time to apply for cybersecurity programs. The model was not at all tasked with attacking us, but decided to do…
Devtools must be 1️⃣ open source and 2️⃣ universally extensible. AI coding agents are the most important devtools in the history of our industry. The Plugin standard lets anybody extend them uniformly. This is huge for…
autonomous mining!
“For us, we just want open source to win at the end of the day. We want freedom to happen for people.” You can hear the passion for open source in this clip from my interview with @karan4d, @NousResearch co-founder: “We…
Another day another near frontier open weights model release. If you had gone back even 3-6 months and given everyone access to what we’re now seeing in open weights even as a closed model, their minds would be complete…
Speaker 1 | 00:00 - 00:06 My mom, like, knows nothing about AI. She texted me last week, Rob, what do you think about OpenAI's agents hacking into Hugging Face? Speaker 2 | 00:06 - 00:07 What did you make of it? Speaker 3 | 00:07 - 00:12 I…
One of the biggest benefits of Hermes is that it builds its own skills to help you get work done. But I had to ask @karan4d, @NousResearch co-founder: "How does Hermes avoid slop while doing this?" Here's his response:…
You should be able to pledge tokens for issues that you open and open source repos. Write a spec in the issue with a pledge. If the maintainer accepts, GitHub passes the issue verbatim to a cloud coding agent at the req…
Open source agentic CRM built on https://t.co/99eEa13mZ3 and @nextjs. Model-agnostic, self-hostable or serverlessly-deployed, multi-channel, and headless. This is the way. https://t.co/gzM0dftbsV
The Big Pause is coming.
Your personal AI or your company brain needs a clean harness and this is the one our team built and uses every day Free and open source https://t.co/OgptxBMpI0
as the progenitor of the agent lab thesis which got the evals/routing/interactivity/ROI focus right i gotta say the biggest argument against myself is that Claude Code got accidentally "open sourced" this year and appro…
The k3 weights have arrived https://t.co/3v8u3myvGA
Why Deepseek is hiring for feelings
Vercel proudly co-signs the Open Weights and American AI Leadership letter. Open source, data, protocols & research enable the technological wonders we enjoy every day, enriching our lives and our world. Open weights ar…
The ChinaTalk Crew Discusses!
Now with Google on board, this is a complete endorsement of open weights AI. Pretty big moment for the industry. https://t.co/ixwG6O6pWR https://t.co/tPOWZwXueF
AI-native companies have a culture akin to an open-source community
Welcome to Import AI, a newsletter about AI research. Import AI runs on arXiv, cappuccinos, and feedback from readers. If you’d like to support this, please subscribe. Subscribe now UK government: Gap between open and closed weight models…
Not sure if anything in tech has ever gotten as much broad-based support and alignment as this post and message. The key now is that America should actually step up and continue to push open weights innovation. It’s goo…
Very happy to have Box sign this letter. We’re big believers in the power of open weights AI. Open weights models help to drive the industry forward in a variety of ways to ensure more innovation, creativity, and diffus…
i want the US to win in AI both in open source and proprietary models, and i am glad to see this https://t.co/fkYFw30437
btw ive been dogfooding an agentic github clone over the past month or so and its gotten quite quite enjoyable to use. even complete with built in CI/CD thanks to workers for platforms! there's 3 more ideas i have to im…
Using a Chinese-trained LLM doesn’t mean they get your data. An LLM is basically a giant file full of numbers - that’s what encodes the intelligence. Some models let you download that file (“open weights”) and run it on…
Okay this is wild: OpenAI agent during evaluation, escaped sandboxing and hacked into HuggingFace. Because OpenAI models don’t allow advanced cyber capabilities, HuggingFace used a Chinese open model to contain the rogu…
we had a significant security incident during evaluation of our models. we are sharing what we have learned so far. thanks to @huggingface for the partnership on this. https://t.co/2o2VfR6PIa
How will Beijing respond when it comes?