Introducing FrontierCode 2.0: our new coding benchmark that measures a model’s ability to go beyond the spec.
Most coding evals measure a model’s ability to write code that meets a spec. With FrontierCode 1.0, we asked a new question: would you actually merge the PR?
FrontierCode 2.0 is comprised of more diverse tasks, featuring larger scopes and higher mergeability standards. We are now asking: not only would you merge this PR, but should you?
One key feature of FrontierCode 2.0 is underspecified prompts. Rather than including every engineering decision, prompts are deliberately ambiguous, giving the models room to demonstrate their judgment.
The result is a benchmark that is far from saturated, with the top model scoring just 45%.
Day 16/
You can now cache for 12h in the API and for logged in users across Codex & Work we keep cache forever and you don’t have any penalty for coming back to an old conversation or resuming after a few hours and are now guaranteed to hit the cache.
While scores at the top of ARC-AGI v1/2 are topping out at 95% there is still a lot the benchmark tell us about efficiency
Not only does GPT-5.6 Sol get 92.5% on ARC-AGI-2 (sota) but it does so at 1 OOM less cost than GPT-5.5 Pro(!)
GPT-5.5 Pro came out 3 months ago...
ComfyUI is the most flexible, composable, and powerful open-source media generation tool with a massive ecosystem of workflows and custom nodes.
Your Hermes Agent can now install, launch, manage, and run sophisticated @ComfyUI workflows on demand.
Ran Google’s cookbook with 10 agents on my tiny GB10 GPU.
436 tok/s / 43.6 per agent
Qwen3.6-35B + Dflash + DDTree on vLLM GB10 @ 74W
The future isn't 10,000 GPUs in a nuclear-powered data center. It’s 10 agents on your desk solving your problems while you make your coffee.
What does it take to run 3, 5, or even 10 concurrent instances of Gemma 4 locally?
We've open-sourced a demo letting you run multiple models side-by-side on your hardware.
Gemma 4 26B A4B easily runs 10+ concurrent requests on a MacBook Pro M4 Max at 18 tokens/sec per request.
Introducing ml-intern, the agent that just automated the post-training team @huggingface
It's an open-source implementation of the real research loop that our ML researchers do every day. You give it a prompt, it researches papers, goes through citations, implements ideas in GPU sandboxes, iterates and builds deeply research-backed models for any use case. All built on the Hugging Face ecosystem.
It can pull off crazy things:
We made it train the best model for scientific reasoning. It went through citations from the official benchmark paper. Found OpenScience and NemoTron-CrossThink, added 7 difficulty-filtered dataset variants from ARC/SciQ/MMLU, and ran 12 SFT runs on Qwen3-1.7B. This pushed the score 10% → 32% on GPQA in under 10h. Claude Code's best: 22.99%.
In healthcare settings it inspected available datasets, concluded they were too low quality, and wrote a script to generate 1100 synthetic data points from scratch for emergencies, hedging, multilingual etc. Then upsampled 50x for training. Beat Codex on HealthBench by 60%.
For competitive mathematics, it wrote a full GRPO script, launched training with A100 GPUs on https://t.co/udm7xGpNzR, watched rewards claim and then collapse, and ran ablations until it succeeded. All fully backed by papers, autonomously.
How it works?
ml-intern makes full use of the HF ecosystem:
- finds papers on arxiv and https://t.co/brvCC7fLPa, reads them fully, walks citation graphs, pulls datasets referenced in methodology sections and on https://t.co/hrJuRkRyzi
- browses the Hub, reads recent docs, inspects datasets and reformats them before training so it doesn't waste GPU hours on bad data
- launches training jobs on HF Jobs if no local GPUs are available, monitors runs, reads its own eval outputs, diagnoses failures, retrains
ml-intern deeply embodies how researchers work and think. It knows how data should look like and what good models feel like.
Releasing it today as a CLI and a web app you can use from your phone/desktop.
CLI: https://t.co/l3K1PslZ1n
Web + mobile: https://t.co/orko5srL4H
And the best part? We also provisioned 1k$ GPU resources and Anthropic credits for the quickest among you to use.
I've officially started a project that I've been wanting to tackle for quite some time. :}
Here is the first installment (of many) intended to detail the entirety of Waterdeep, ward-by-ward and building-by-building!
#dnd#bg3#realmslore
🎥 ▶️ https://t.co/oe0TiOygKb
So You Want To Be a Game Master features an entire chapter about your Supporting Cast, a grab bag of tools & tricks for creating & running memorable NPCs.
The book comes out in two days!
Join its supporting cast by helping to spread the word!
Can't wait to hear what you think!
I would like to announce the upcoming Stardew Valley Cookbook! It'll be out next spring, and includes 50 recipes from the game... such as pink cake, salad, and the strange bun. Cover illustration by @kee_fry
We didn’t get any exclusives, but we got a look at the announcement and PR and it looks like everything is going to be moving forward a lot faster than expected! Vox Machine is going to season 3, Mighty Nein is in development… Critters stay winning.
https://t.co/caGWTtyga9