AI Dynamics

Global AI News Aggregator

About

@thom_wolf

  • Chroma Context-1: Open-source 20B Search Agent Released

    By

    @thom_wolf

    –

    Introducing Chroma Context-1, a 20B parameter search agent. > pushes the pareto frontier of agentic search > order of magnitude faster > order of magnitude cheaper > Apache 2.0, open-source

    → View original post on X — @thom_wolf, 2026-03-26 19:01 UTC

  • Beyond Random Search: Guiding Autoresearch Agents Toward Meaningful Exploration

    By

    @thom_wolf

    –

    What are the best current techniques to have autoresearch behave better than (slightly improved) random search? By which I mean (in Sijun below example), having the agent understand that (given some constraints) exploring int5 quantization is more exciting and have more downstream fruits than playing with the random seed? I’m talking about the beginning of having an agent pushed a real research program. The ones where you know the current technique will not give crazy results out of the box but it still push it because it believe and can demonstrate that the general direction has potential. Like neural networks used to be a worse way to do AI performance-wise. But we still pushed them… Sijun Tan (@sijun_tan) We took @karpathy's autoresearch agent, scaled it into a collaborative swarm, and topped @OpenAI's Parameter Golf Challenge—twice. Here’s how we did it: — https://nitter.net/sijun_tan/status/2036584756729749802#m

    → View original post on X — @thom_wolf, 2026-03-25 12:29 UTC

  • Auto-Research for Data: The Underrated ML Game Changer

    By

    @thom_wolf

    –

    Auto-research for ML training models is all the rage now, but underrated is: auto-research for data! Sure, you can squeeze out a bit of model performance by optimizing hyperparameters, but code agents can do data work that has been very labour intensive and required a lot of attention to a lot details effortlessly: > download data from many different data sources > bring all the data sources into uniform format > do detailed EDA: find patterns and outliers > look at 100s of samples and take detailed notes > make beautiful infographics rather than mpl plots > iterate on data filtering by looking at more samples > make a simple pipelines robust and scalable It's now possible to write data pipelines for dozens of data sources in hours that would have taken weeks of reading many docs, debugging APIs and data formats, wrangling outliers and missing data. A few weeks ago we gave Claude access to the CPU partition of our cluster and it iteratively refined filters to retrieve a domain subset of FineWeb. This would have taken me 2-3 days to work through while it took Claude just a few hours with almost no babysitting and with a nice logbook. Thus the long tail of small, niche data sources becomes more accessible and can be aggregated to even larger high quality datasets for cool applications. Data has been fuelling LLM progress more than model architecture innovations, so I am very excited about this!

    → View original post on X — @thom_wolf, 2026-03-24 17:04 UTC

  • hf-mount: Mount Hugging Face datasets and models as local filesystems
    hf-mount: Mount Hugging Face datasets and models as local filesystems

    By

    @thom_wolf

    –

    Now available on Hugging Face: hf-mount 🧑‍🚀 The team really cooked, still wrapping my head everything possible but you can do things like: – mount a 5TB dataset as a local folder and query only the parts you need with DuckDB (✅ works) – browse any model repo with ls/cat like it's a USB drive – use a shared read-write bucket as a team drive for ML artifacts – drop the init container that downloads models in your k8s pods – point llama.cpp at a mounted GGUF and run inference (infinite storage??)

    → View original post on X — @thom_wolf, 2026-03-24 16:13 UTC

  • hf-mount: Mount Hugging Face Storage as Local Filesystem
    hf-mount: Mount Hugging Face Storage as Local Filesystem

    By

    @thom_wolf

    –

    hf-mount Attach any Storage Bucket, model or dataset from @huggingface as a local filesystem This is a game changer, as it allows you to attach remote storage that is 100x bigger than your local machine's disk. This is also perfect for Agentic storage!! Read-write for Storage Buckets, read-only for models and datasets. Here's an example with FineWeb-edu (a 5TB slice of the Web): 1️⃣> hf-mount start repo datasets/HuggingFaceFW/fineweb-edu /tmp/fineweb It takes a few seconds to mount, and then: 2️⃣> du -h -d1 /tmp/fineweb 4.1T ./data 1.2T ./sample 5.3T . 🤯😮 Two backends are available: NFS (recommended) and FUSE Let's f**ing go 💪

    → View original post on X — @thom_wolf, 2026-03-24 13:34 UTC

  • LiteLLM Compromise: Malicious Update Alert Version 1.82.8

    By

    @thom_wolf

    –

    LiteLLM HAS BEEN COMPROMISED, DO NOT UPDATE. We just discovered that LiteLLM pypi release 1.82.8 has been compromised. It contains litellm_init.pth with base64 encoded instructions to send all the credentials it can find to a remote server and self-replicate. Link below [Translated from EN to English]

    → View original post on X — @thom_wolf, 2026-03-24 12:06 UTC

  • Pretraining LLMs entirely on Hugging Face Hub infrastructure

    By

    @thom_wolf

    –

    You can now pretrain LLMs entirely on the HF Hub 💥 Last week, @OpenAI launched a competition to see who can pretrain the best LLM in under 10 minutes. So over the weekend, I made a little demo to automate this end-to-end using the Hub as the infra layer: – Jobs to scale compute – Buckets to store all experiments – Trackio to log all the metrics The cool thing here is that everything is launched locally: no ssh shenanigans into a cluster or fighting with colleagues over storage and GPUs ⚔️ All that's left is coming up with new ideas, but luckily Codex can automate that part too 😁 Can I have a job now please @reach_vb 🙏?

    → View original post on X — @thom_wolf, 2026-03-23 16:29 UTC

  • The Future of Open Source: From Code to Data and Beyond

    By

    @thom_wolf

    –

    is the future value of "open source" code anymore? i believe it's shifting to data, provenance, protocols, evals, and weights. in that order.

    → View original post on X — @thom_wolf, 2026-03-22 23:49 UTC

  • Using Hugging Face Papers API as an AI Development Skill
    Using Hugging Face Papers API as an AI Development Skill

    By

    @thom_wolf

    –

    If you're building anything in AI, the best skill you need to be using right now is hugging-face-paper-pages Whatever problem you're facing, someone has probably already published a paper about it. HF's Papers API gives a hybrid semantic search over AI papers. I wrote an internal skill, context-research, that orchestrates the HF Papers API into a research pipeline. It runs five parallel searches with keyword variants, triages by relevance and recency, fetches full paper content as markdown, then reads the actual methodology and results sections. The skill also chains into a deep research API that crawls the broader web to complement the academic findings. The gap between "a paper was published" and "a practitioner applies the insight" is shrinking, and I think this is a practical way to provide relevant context to coding agents. So you should write a skill on top of the HF Paper skill that teaches the model how to think about research, not just what to search for.

    → View original post on X — @thom_wolf, 2026-03-22 18:35 UTC

  • RL Model Transferability: Personalizing Across Rapidly Evolving Base Models
    RL Model Transferability: Personalizing Across Rapidly Evolving Base Models

    By

    @thom_wolf

    –

    This is really cool. It got me thinking more deeply about personalized RL: what’s the real point of personalizing a model in a world where base models can become obsolete so quickly? The reality in AI is that new models ship every few weeks, each better than the last. And the pace is only accelerating, as we see on the Hugging Face Hub. We are not far away from better base models dropping daily. There’s a research gap in RL here that almost no one is working on. Most LLM personalization research assumes a fixed base model, but very few ask what happens to that personalization when you swap the base model. Think about going from Llama 3 to Llama 4. All the tuned preferences, reward signals, and LoRAs are suddenly tied to yesterday’s model. As a user or a team, you don’t want to reteach every new model your preferences. But you also don’t want to be stuck on an older one just because it knows you. We could call this "RL model transferability": how can an RL trace, a reward signal, or a preference representation trained on model N be distilled, stored, and automatically reapplied to model N+1 without too much user involvement? We solved that in SFT where a training dataset can be stored and reused to train a future model. We also tackled a version of that in RLHF phases somehow but it remain unclear more generally when using RL deployed in the real world. There are some related threads (RLTR for transferable reasoning traces, P-RLHF and PREMIUM for model-agnostic user representations, HCP for portable preference protocols) but the full loop seems under-studied to me. Some of these questions are about off-policy but other are about capabilities versus personalization: which of the old customizations/fixes does the new model already handle out of the box, and which ones are actually user/team-specific to ever be solved by default? That you would store in a skill for now but that RL allow to extend beyond the written guidance level. I have surely missed some work so please post any good work you’ve seen on this topic in the comments. Ronak Malde (@rronak_) This paper is almost too good that I didn't want to share it Ignore the OpenClaw clickbait, OPD + RL on real agentic tasks with significant results is very exciting, and moves us away from needing verifiable rewards Authors: @YinjieW2024 Xuyang Chen, Xialong Jin, @MengdiWang10 @LingYang_PU — https://nitter.net/rronak_/status/2034158978733904160#m

    → View original post on X — @thom_wolf, 2026-03-19 15:01 UTC