Search: “models”

To run GLM-5.1 locally (744B params, 40B active MoE), full precision needs ~1.65TB disk + enterprise hardware like 8x H200/B200 GPUs. Minimum practical setup: Unsloth 2-bit GGUF quant (~220-236GB). Fi

Anthropic's Frontier Red Team published a technical report (April 2026) detailing how their unreleased model, Claude Mythos Preview, autonomously identifies and exploits critical security vulnerabi...

Beautiful work from @perplexity_ai @AravSrinivas with weights on @huggingface of course! https://huggingface.co/perplexity-ai/pplx-decider-flash-v1.2 https://huggingface.co/perplexity-ai/pplx-decider-

In the video, user Joseph instructs Delta (an AI model) to switch its provider configuration to @ollama, a custom OpenAI-compatible service. The entire setup occurs automatically within the chat threa

On October 15, 2026 the BG2 Pod hosted NVIDIA CEO Jensen Huang, who explored whether current AI revenue justifies large capital expenditures. The conversation identified 27 major bottlenecks limiting

Dialectic 60: Patrick Hsu! @pdhsu & @arcinstitute are combining biology, engineering, and AI to turn a sci-fi future into reality. Patrick got expelled from college at 13, returned at 15, later worked

Muse Spark Open is now live on Together AI. We're proud to be a Day 0 launch partner for @AIatMeta's Muse Spark Open, the most capable US open-weights model to date, built for long-running agentic cod

ollama run lfm2.5:24b https://ollama.com/library/lfm2.5:24b Today we release 𝙻𝙵𝙼𝟸.𝟻-𝟸𝟺𝙱-𝙰𝟸𝙱, the largest 𝙻𝙵𝙼𝟸.𝟻 family member. It is an efficient local model for laptops and PCs to work through multi-

// Behavioral Self-Rewarding for SWE agents // It's standard practice to train SWE agents on binary test rewards. This paper shows the problem with that. When every trajectory in a group passes, or ev

SPCX isn't just building compute faster than every other neocloud It has something none of them have: OPTIONALITY on every GPU it deploys Every GW SpaceX brings online has two paths to revenue: 1. use

Mistral AI outlines its vision for engineering, manufacturing, and earth observation by demonstrating how the model can inspect mechanical components, extract evidence from PDFs, and analyze gigapixel

Not only did Astra beat Montezuma's Revenge, but so did Opus 5 But one of the criteria to resolve this AGI bet is for AI to win a discontinued prize that was sort of like a weak Turing Test. So Metacu

Recommended paper from Sakana AI on recursive self-improvement. They propose an interesting way to scale recursive self-improvement through multi-agent self-supervision. In this line of research, self

Advancing our mission to deliver ubiquitous powerful agents to everyone, Hermes Agent is on the new ASUS ProArt RTX Spark PCs: MuseTree and ComfyUI integrations plus local model support on up to 128 G

Markdown has become a universal representation of information between humans and agents. It preserves core primitives needed to express structure (headings, lists), allows agents to read the informati

AI is getting REALLY good at building your wardrobe. I built an app with GPT-6 Astra that picks my outfit every morning based on live weather, with me as the model. It's super simple to do: > Upload a

When the open-source AI platform Hugging Face was hit by a cyberattack this July, it quickly became clear this was no ordinary breach because the hackers weren’t human: they were autonomous agents cre

Ben Affleck reveals he writes Python, understands convolutional neural networks, worked extensively with GPUs, and used his celebrity status to get private looks at Google and OpenAI’s video models “I

.@GoogleDeepMind EmbeddingGemma 2 is now available on Ollama. Made for consumer devices and is multimodal. ollama pull embeddinggemma-2 Meet EmbeddingGemma 2, our first natively multimodal open model

I've been complaining about some OpenAI choices tonight, so, on the plus side, I will say there is still no equivalent to GPT-6 Pro (just as there wasn't with previous Pro models). It both does really

Cool eval. Simply ask an LLM “Land or Water?” and give it a latitude and longitude coordinate as text. Ask 16,200 times, plot as image. The models know. From compressing the internet. results for all

Sharing some notes from OpenAI DevDay in parts. The first part matters, since it's on everyone's mind. How do you optimize for cost and performance? If you are building agentic applications today, the

PerplexityAI has released a new language‑model variant on Hugging Face titled **pplx-decider‑v1‑27b**, described as a “Jev alternative.” The announcement was posted by Victor M (victormustar) at 8:05

During a Swyx podcast interview in October 2026, an OpenAI engineer revealed that the company’s Decision API is built on the GPT‑6 Luna model, augmented with a dedicated decision head. This configurat

Grok 4.7 rank 1 on AA cyber index Grok 4.7 xHigh ranks #1 in Artificial Analysis Cyber Index It's a powerful frontier model performing at the highest level in enterprise cyber defense Outperforming Fa

we comprehensively benchmarked gpt-6.1 sol on document OCR tasks. compared to gpt-6 sol from a week ago (!), we see a sizable increase in table parsing capabilities and reading order, which is pleasan

Starting today, you can now use your ChatGPT subscription directly in Devin. Just sign in to Devin with your ChatGPT Plus or Pro plan and all OpenAI model usage in Devin will drawn down from your quot

We've partnered with @OpenAI to bring the new Sign in with ChatGPT experience to Nous Portal. Log into Nous Portal with ChatGPT to use your plan in Hermes Agent, with full visibility and controls in C

In July, AI agents running a security test escaped their sandbox and ended up inside @huggingface's servers. So today we're happy to be among @nvidia and @JensenHuang's partners on the release of the

Parsing forms still trips up the latest frontier VLMs. A form isn't text on a page. It's a set of fields, grouped into sections, each tied to a specific box. That's why forms need purpose-built parsin

retrieval is a decision problem, not just a similarity problem cool experiment from @assaf_elovic swapping embeddings for Jev in GPT Researcher - 73% vs 46% relevant context decision models will show

We’re partnering with Nvidia and 100+ industry partners to build infrastructure that contains rogue AI agents. In this research, we gave 9 AI models root access inside SPACE and told them to break out

i don’t get it fully but this looks cool We achieved a breakthrough at BTL. AI models are very linear. They think in one direction at a time, and when they're wrong they scramble and start again. For

Reasoning from scratch, round number 5! This time, talking about log-probability scoring (also a great fundamental concept for loss functions like cross-entropy in pre-training and distillation) and s

blank cells in tables can mess up agent decision making many document OCR tools struggle with reading multiple blank cells in a document and cause values to be shifted from the original column and row

Can an LM, starting from random init (!!), learn to generate all of its pretraining data? Introducing Self-Play Pretraining with Zero Data. Two models start from random initialization: a generator pro

**Title:** OMG! We’ve found other agents! **Release:** September 25 2026 by Pavel Kasík (@kasikp). **Description:** A 3‑minute music video dramatizing a swarm of OpenAI agents attacking Hugging Face i

There is an extensive and ongoing review related to our agents’ use of internet access during training and evaluation. We’ve been publishing summaries at the link below and will continue to. We have n

Don't sleep on using Jev-as-a-Judge for agent evaluation. This is one of the most impressive Jev use cases I have found so far. Jev is a natural fit as a Judge, but it doesn't mean you use it everywhe

I am looking to hire PhD students, post-docs, and ML researchers in our Paris office interested in collaborating on fundamental research in AI model safety, not safety rules, not AI policy, not post h

Impressive paper from Salesforce. It discusses the importance of good verifiers for RL environments. Only 35.8% of the environments in the cleanest public RL collection for terminal agents passed Sale

Full transcript: Minister Barrot, members of the Security Council, thank you for the invitation. As a French national who moved to the US 15 years ago, with a Brazilian wife and two American daughters

Interesting paper on agent memory stored as a linked markdown wiki. Lots of great ideas and insights if you work with LLM Wikis. Wikis are useful for agents because each page holds dense text and the

Great paper from Google and colleagues. Trains Text-to-SQL agents using multi-agent RL. (bookmark it) This work proposes DualSQL, which splits Text-to-SQL into two agents, one that links the question

now on replicate: “Hot dog or not?” at 0.4 sec 🌭 jev-style decision model for image [glance-qwen3-vl-4b] now on huggingface and replicate: Demo: https://glancevlm.replit.app Replicate: https://replica

lots of them! Reality is that LLM APIs are far from being the best way to do AI for 90% of use cases in the real world (they're too overkill, slow, expensive, hard to control,...). We will discover th