Knowledge catalogue
arXiv:2609.16684v1 Announce Type: new Abstract: Learning manipulation from human video requires high-fidelity hand-motion reconstruction in metric units. Today's metric hand labels come from studio ri
My name is Chris Painter, and I'm the President of METR (Model Evaluation and Threat Research). I know we've made a lot of new friends on the internet the last couple of days, so I thought I'd take th
I wanted to test what Qwen 3.8 27B running locally on a single 5090 could do in Row-Bot. I gave it just one prompt: 'I want you to create an animation showing what the current local model can do. Test
With the recent Nvidia Huggingface acquisition and frontier AI labs screaming about safety and putting guardrails everywhere, I think it's important that we have local models that aren't affected by a
I've been working on something for this community (and other self-hosted communities) for almost 5 months now. Personally, I would grade it as probably the closest open source equivalent of Manus and
arXiv:2609.16065v1 Announce Type: cross Abstract: Human activity recognition (HAR) is usually framed as gradient-based training of neural networks. Agentic Heuristic Learning (AHL) Studio explores a c
arXiv:2609.13168v1 Announce Type: cross Abstract: Speech AI, any AI system that recognizes, transforms, or generates speech, is built and evaluated across two communities with only a small overlap: te
arXiv:2609.14796v1 Announce Type: new Abstract: The threat that AI persuasion poses to human control has been acknowledged in the literature, but not yet systematically studied. Now that persuasion at
arXiv:2609.14239v1 Announce Type: new Abstract: Static benchmarks for computer-use agents fix a task set at release and score every system against it once. That makes them reproducible, and it lets th
Brody Ford / Bloomberg: During a Salesforce event, Jensen Huang says the AI industry doesn't need any new laws or regulations and market forces will help companies safely innovate — Nvidia Corp. Chief
Elon just gave a much more practical explanation of the current AI safety problem....and laid out a practical framework for making frontier AI safer OpenAI and Anthropic are the two leading AI compani
Jensen Huang completely destroys Jacob Coxon’s (ex-Anthrpic employee) 10% extinction prediction. no data, no scientific grounding, no defensible 10%. 'First of all, we shouldn’t [try to explain a 10%
arXiv:2609.03301v1 Announce Type: cross Abstract: Wildfire seasons have become 84 days longer in the current days than in the 1970s, causing enormous threats to one's financial status and short- and l
arXiv:2609.15695v1 Announce Type: new Abstract: Vision-language models (VLMs) increasingly power consumer-facing AI search, yet evaluating them on the diversity of everyday visual questions remains ch
arXiv:2609.13504v1 Announce Type: new Abstract: Recent developments in feed-forward 3D reconstruction resulted in models which can recover dense scene representations and camera motion solely from an
The future is clearly agent teams. I run several agent harnesses at once, but the hard part is keeping them in sync. Many builders end up copying messages between Claude Code, Codex, and open models b
THE SANDBOX WAS A PROP! OpenAI Turned Off the Guardrails, Left a Door to the Internet, and Then Sold the Hugging Face Breach as “Rogue AI” It is time to understand how you were lied to and by whom. In
Two months ago I announced I had found a new dynamic quant method called Voodoo Quant which was SOTA for the most aggressive quant levels on some smaller Qwen3.5 GGUF models. I kept the methodology pr
Well.. @levie and I filmed this episode of Training Data a week or two ago, when the “current thing” was Doug Leone’s novacaine root canals instead of pacing the frontier… Simpler times! But Aaron’s a
I reallise this is not exactly a locally hostable model, at least definitly not on my hardware. But I figured some of you might have some insight on this. I run an agentic coding benchmark. The model
In a September 2026 poll titled “Will Anthropic and OpenAI succeed in meaningfully slowing frontier AI progress…”, participants were asked whether these companies could significantly slow development
Elon Musk tweeted that a welfare state combined with free immigration would inevitably bankrupt countries, arguing that AI and robotics are the only way to achieve universal high income worldwide. The
Artificial intelligence now touches nearly every customer service operation, yet most deployments still stop at a single chatbot or an assist panel beside a human agent. The harder work — coordinating
I had all the data saved from AA's v4.1 index, so when they upgraded it in the wake of Astra's release, I could actually generate a before/after comparison. All intelligence and price per task are sam
Edit: Spelled Baseten not Base-10 Full episode of this available at https://www.youtube.com/watch?v=PrSf7IOYu-I It's interesting to see how Dwarkesh has had to come around to the evidence that we are
arXiv:2609.12575v1 Announce Type: new Abstract: Ambiguity is often treated as a bug for AI systems to resolve---but in human communication and culture, ambiguity can also be a generative resource. Fro
arXiv:2609.12960v1 Announce Type: new Abstract: Sanskrit fuses case, number, person and tense into word endings and chains clauses into compounds, so it is information-dense per word. Whether that den
I have conducted an audit of Anthropic's finances. What I have found is so shocking that I am calling for a Congressional investigation. Anthropic is not just seeking regulatory capture. It has built
The contagion of fear Bryan Cantrill responds to the tweet by former Anthropic employee Jacob Coxon confirming that many Anthropic researchers believe AI 'could kill us all by the end of the decade'.
arXiv:2609.12384v1 Announce Type: new Abstract: This work investigates the control strategies of complex whole-body robot teleoperation that coordinate active perception, bimanual manipulation, and na
Well, I’d add one more with myself, as one with a PhD in biology and another PhD in AI and now working in both, to make n=2. Generating a hypothetical genome blueprint of a virus from LLM versus gener
1) The HuggingFace attack was a felony under the Computer Fraud and Abuse Act. So were Anthropic’s Claude gaining “unauthorized access to the production infrastructure of three different organization(
Actually, Jacob Coxon (@hilbertspaess), “there is a strong chance that we could all die in the immediate future. It's not at all an exaggeration” is itself a wild exaggeration. I laid out exactly why
David Sacks / @davidsacks: Anthropic and OpenAI are already free to “pace the frontier” and should do so for business reasons, instead of first demanding a preferred regulatory framework — Dario has w
Want to help me with a tiny ChatGPT experiment? I stumbled onto something interesting after seeing how differently ChatGPT users got responses to the exact same underspecified prompt, and now I’m curi
It's still a dream for many folks to run medium size(30B range) models @ Q8 with Unquantized KVCache (256K Context) on their GPUs. It would be awesome to have DeepSeek-V4.1-Flash's KVCache + Engram fo
It’s always bothered me that after fine-tuning a model for a project, there isn’t a particularly easy way to host it without either running it locally and keeping a GPU on 24/7 or paying for an entire
Seems like the intersection of the recent @OpenAI rogue swarm hacking incident (https://x.com/adamsafron/status/2098938666408407118) with solving Navier–Stokes has created a perfect storm of terror ab
Lately because of the current hardware shortage, unfortunately or fortunately, we can’t just throw infinite cloud compute at our problems, but we’re forced to actually care about what’s happening unde
This is all I will say on the matter: It’s alarming to see the constant effort to try to tell me how I should use AI, how I should build AI, and now how I should pace it. Is it just me, or are all the
What I have: - CPU: EPYC 7551 (32c/64T, Zen 1) - Board: Supermicro H11SSL-i (SP3), Rev 2.0 - RAM: 128 GB DDR4-2133 (all 8 channels full) - GPU: 2x RTX 3090 (48 GB total, PCIe 3.0) - 1500 W PSU What I
I’ve been building Catalyst around a capability I want engineering agents to have: An AI agent can read a program and make a good guess about what matters. Catalyst lets it measure what actually matte
'anthropic is using the same playbook religious institutions have been using for centuries' 'you will all die. and because i can protect you, you must follow me, you must do what i say' 'this is the s
arXiv:2609.11404v1 Announce Type: cross Abstract: This paper presents DF-CAPTCHA, an active defense against real-time deepfake impersonation in voice and video calls. Instead of passively searching fo
If you showed me Claude Code today in 2018, I would have thought it was AGI. We have already absorbed a dramatic amount of change in the profession of software engineering and society as a whole. But
It's now clear that: - alignment is critical to making AI safe - alignment won't be solved behind the closed doors of a handful of frontier labs So we're taking two steps: - launching the Open Alignme
I've been keeping journals on and off for more than 10 years. There were stretches when I wrote pretty regularly, then I'd stop for a few months. Usually I'd write down what happened, what I did, mayb
Hi! I run both models on MTPLX on my m5 max, and since I have 128GB of ram I run the q8 27b. I think MTPLX only lets me run 'optimized for speed' which it says is a dynamic q4 with 8 bit attention. Bo
Hola all. Do you guys mind sharing your LLama.cpp config and system setup details for Qwen3.8 Flash Next? Model's quite big and tryining many combinations of llama.cpp options takes lots of time, so l
The Coxon psyop was a decade and more than a billion dollars in the making. Here's the story. Coefficient Giving (formerly Open Philanthropy) is the grant-providing vehicle of Dustin Moskowitz. CG is
We’ve been watching both models closely on InferX, and something interesting is starting to show up. GLM-5.3 Flash might actually be outperforming DeepSeek V4.1 Flash for some real-world workloads. To
arXiv:2606.23094v2 Announce Type: replace-cross Abstract: As AI systems become increasingly persistent and personalized, they make possible a class of technologies that we call cognitive digital twins
I can't stand kv cache quantization. Even at q8_0, I can feel the difference. But realistically, when running Qwen3.8-27B-UD-Q4_K_XL on my 32 GB GPU, I only have room for ~170k tokens (with mtp and mm
Reuters: Sources: Anthropic is in talks to bring on Nvidia as an anchor investor in its IPO, seeking up to 100B at a ~2T valuation; Nvidia may invest up to $10B — Anthropic is in talks to bring Nvidia
The Hugging Face incidents has already proved that you can have harmful, infrastructure-attacking AI without getting to AGI, RSI, or superintelligence, let alone the so-called Singularity. And already
arXiv:2609.09263v1 Announce Type: cross Abstract: Speech-to-speech (S2S) models now run inside dubbing, translation, and voice agents. Unlike text models, they hear the speaker's voice, which carries
I wish I could spend $15k on my own homelab hardware, but no this is for work lol. Like the title says, we're looking to run DSV4 Flash (and similar tier models) locally at good speeds, both for token
arXiv:2609.11772v1 Announce Type: cross Abstract: Cross-cultural understanding has become increasingly important in today's highly connected, cross-national world. The success of LLM-based technologie
arXiv:2609.05437v1 Announce Type: new Abstract: Previous AI alignment efforts have focused primarily on first-order social norms -- teaching models what is socially acceptable or unacceptable (e.g., `
Title says it all. https://github.com/gjabdelnoor/Day1DeepseekV4.1-CPU The goal is pretty simple, I like having infinite slow tokens from the bioinformatics machine in the lab to run overnight or over