Latest stories
Albertsons Taps ChatGPT Enterprise and OpenAI API to Reinvent Grocery Retail
Albertsons Companies is deploying ChatGPT Enterprise and the OpenAI API to speed up internal work and improve the grocery experien...
Barclays Expands Anthropic Partnership, Targets Claude Code for Majority of Engineers by 2027
Barclays is scaling Anthropic's Claude across its global operations, expecting Claude Code adoption to reach half its developers b...
LANTERN Uses Model Activations to Uncover Hidden Math Links in OEIS
A new pipeline called LANTERN ranks candidate relations between integer sequences using a classifier over pretrained-model activat...
Hugging Face Paper Unveils 50,000-Pair Agent Error Dataset for Failure-Aware Training
The Agent Error Dataset (AED) compiles 50,228 error-diagnosis pairs drawn from 9,961 tasks across 33 environments, and its five-st...
Hugging Face Paper Introduces AIM: An Agentic Framework for Managing Research Ideas
A new paper proposes the Agentic Idea Manager (AIM), a fully autonomous framework that organizes, selects, and audits research ide...
LoopVL Brings Recurrent Computation to Vision-Language Models
Hugging Face paper LoopVL explores whether Loop Transformers can be extended to vision-language models, combining Module-Loop and...
Hugging Face Paper Exposes 'Ordinal Scale-Utilization Bias' in Direct-Decision Models
A new study of JEV 1.13 and three open KEV models finds that direct-decision models compress the ordinal scales users supply, usin...
Imagine3D-LLM Teaches Multimodal Models to Picture 3D Scenes Before Answering
A new Hugging Face paper proposes Imagine3D-LLM, a multimodal model that builds a compact 3D Gaussian Splatting representation of...
Hugging Face Paper Asks Whether AI Agents Know When to Ignore Bad Advice
A new Hugging Face paper introduces Box²-Bench, a benchmark that varies workflow reliability while holding model and task fixed, t...
EVOKE Trains LLM Agents to Use World Knowledge They Already Have
A new post-training method from Hugging Face researchers, EVOKE, holds environment states fixed while swapping in alternative goal...
RSIGame Brings Recursive Self-Improvement to Autonomous Game Development
A new Hugging Face paper introduces RSIGame, an agentic framework that pairs local explore-diagnose-improve loops with a global qu...
Mid-Harness Boosts Terminal Agent Reliability by Verifying Actions Before Execution
A new Hugging Face paper introduces Mid-Harness, a method that samples and verifies candidate actions at the model-harness boundar...