Latest stories
OpenAI Expands Daybreak with GPT-5.6-Cyber for Authorized Security Testing
OpenAI introduces GPT-5.6-Cyber, a cybersecurity-specific model available through Daybreak Red for authorized vulnerability resear...
OpenAI Expands Access to Frontier Cyber Models for Trusted Partners
OpenAI announces that approved Daybreak partners can now use its frontier cyber models to provide authorized and governed cybersec...
DeepSeek V4 Launches with 1.6T Parameters, Claims 10-50x Cheaper Pricing
DeepSeek unveiled its V4 model family on April 24, 2026, featuring two text-only variants with up to 1.6 trillion parameters and a...
DuplexGen: Calibrating AI Turn-Taking to Human Preferences
New framework DuplexGen generates dialogues with scenario-adaptive turn-taking by calibrating LLM predictions against human prefer...
New 'Skaling' Law Couples Model Size and Data to Sharpen AI Loss Predictions
Researchers introduce the Skaling law, a generalized scaling law that couples model capacity and data via an interaction exponent,...
Multi-Agent Framework and 100K Benchmark Boost Deepfake Video Detection
Researchers introduce FaceVid-Forensics-100K, a large-scale deepfake video benchmark with fine-grained annotations, and ARGUS, a m...
Hugging Face Unveils DME: A Two-Stage Multimodal Embedding Model for Billion-Scale Search
Douyin's DME combines contrastive pre-training with training-only reasoning and reconstruction to achieve state-of-the-art results...
Hugging Face Study: Offline Top-K Distillation Cuts Memory, Boosts Throughput
A new paper from Hugging Face shows that caching teacher logits and using a chunked KL loss can make knowledge distillation for sm...
Small Cognitive Models Match Giants In-Distribution but Scale Better Out-of-Distribution
New research shows that small language models fine-tuned on human behavioral data can match a 70B baseline in-distribution, but la...
Referential Dangling: A Hidden Failure Mode in Hard Prompt Compression
New research from Hugging Face reveals that hard prompt compression methods often delete the context needed to interpret retained...
Fine-Tuned Activation Oracles Develop Concept-Specific Blind Spots, Study Finds
New research from Hugging Face reveals that fine-tuning activation oracles on a subject model that hides a concept makes them sele...
DCAS: Decoupling Scaffold Planning to Make CLI Agents Generalize
A new interception layer, DCAS, decouples planning from scaffold-specific training, enabling fine-tuned CLI coding agents to gener...