Can LLMs Engineer Their Own Agent Harness? ByteDance Seed’s HarnessDev Says Only 34 of 64 Changes Generalize
ByteDance Seed, SUTD, Georgia Tech, M-A-P, and TokenWave.AI introduce HarnessDev, a benchmark that scores the runnable harness a model builds rather than the answer it returns. Starting from a seed that scores 0, 6 creator LLMs construct harnesses across 5 benchmarks and 2,207 tasks, then evolve the...
Anthropic Adds Plugin Evals to Claude Code: 6 Grader Types, a No-Plugin Baseline, and a CI Gate for Skills
Anthropic has published a new plugin evals workflow for Claude Code. The claude plugin eval command runs a plugin against realistic prompts, grades what Claude produced, and compares the result with a run where the plugin is not loaded. It answers 3 questions plugin developers could not previously m...
Kimi-maker Moonshot AI targets $2 billion in annual revenue
While K3's usage figures have declined slightly in recent months, OpenRouter data currently shows as many as 300 billion tokens being generated each day by K3 models on the system.
OpenAI has released ChatGPT Images 2.5, its latest image-generation model, with a greater emphasis on controlled editing than simply producing prettier images. The update promises sharper details, more natural lighting and textures, stronger reference-image preservation, more reliable multi-turn edi...
The most consequential AI news of the past year came from a standards body. In December 2025, Anthropic donated the Model Context Protocol to the newly formed Agentic AI Foundation, a directed fund under the Linux Foundation cofounded by Anthropic, Block, and OpenAI, with support from Google, Micros...
Coding Agents Don't Need Longer History — They Need Intent Continuity
I built a system that automatically discovers, verifies, and applies relevant requirements from earlier interactions without asking the user where they came from.
The post Coding Agents Don't Need Longer History — They Need Intent Continuity appeared first on Towards Data Science.
Lifesaving Lincoln Laboratory device wins 2026 Excellence in Technology Transfer Award
The handheld catheterization device AI-GUIDE, created by Lincoln Laboratory and Massachusetts General Hospital, promises improved health outcomes for injured service members and civilians.
5 Python Techniques for Efficient Resource Orchestration
This article explains 5 Python techniques for efficient resource orchestration and sticks to what's stable today, 3.11 and later for the core techniques, with one 3.14-specific tool called out explicitly as requiring that version
Operating Mode as Runtime State: A Contract for Enterprise
During a service incident, a customer-remediation workflow is moved onto an emergency route because the situation is critical and the team needs a fast resolution. Approvals are shortened, a priority queue is opened, and an on-call agent is cleared to use an alternate procedure until the service rec...
Rapidly scaling online storage to serve over 1 billion ChatGPT users
Learn how OpenAI evolved Habitat from a Python library into a globally distributed storage platform serving 1 billion ChatGPT users and 22M requests per second.
Cohere Releases North Small Translate: A 218B MoE Translation Model That Scores 83.6 on WMT26 Across 50 Languages
Cohere has released North Small Translate, an open-weight Mixture-of-Experts model built for machine translation across 50 languages. It uses 25B of its 218B parameters per token and scores 83.6 on Cohere's WMT26 evaluation. Weights are free for non-commercial use, with commercial access through Coh...
Sakana AI Launches Fugu Max and Fugu Ultra v2 for Cheaper, Stronger Multi-Agent Orchestration
Sakana AI has released Fugu Max and Fugu Ultra v2, 2 models built on the same learned orchestration architecture. Fugu Max routes tasks to lean open and specialized models, including NVIDIA Nemotron, at $2/$6 per 1M tokens. Fugu Ultra v2 targets peak capability, scoring 48.3 on Chartography and 74.3...
Google Research Releases ToolGrad: Answer-First Framework Hits 99.8% Pass Rate for Tool-Use Data Generation
Google Research has released ToolGrad, an ACL 2026 Findings framework that inverts tool-use dataset generation: it builds a verified API chain first, then writes the matching user query. Guided by textual "gradients" from a 4-module propose-execute-select-update loop, ToolGrad reaches a 99.8% pass r...
M3-Former: Multimodal Transformer with Mixture-of-Experts for Long-Term Vessel Trajectory Prediction
arXiv:2609.10559v1 Announce Type: new
Abstract: To address the challenges of behavioral multimodality, limited semantic utilization, and long-term error accumulation in vessel trajectory prediction, this paper proposes M3-Former, a multimodal trajectory prediction framework enhanced by large langua...
DiscoSign: Discourse-Aware Text to Sign Language Gloss Translation
Sign language processing systems have traditionally operated at the sentence level, ignoring critical discourse phenomena fundamental to sign language comprehension. We introduce DiscoSign, a computational approach for discourse-aware text to sign language gloss translation grounded in linguistic re...
Putting Captions to the Test: Evaluating Video Caption Quality through Multiple-Choice Question Answering
Evaluating video captioning remains a critical challenge for Visual Large Language Models (VLLMs). Existing metrics primarily rely on matching generated text against ground-truth references. This paradigm suffers from the “one-to-many” nature of video description, where high-quality captions are oft...
SimpleDesign: A Joint Model for Protein Sequence and Structure Codesign
Proteins are fundamental to biological processes, with their function determined by the complex interplay between the amino acid sequence and the three-dimensional structure. Developing generative models capable of understanding this intrinsically multi-modal relationship is crucial for fields like ...
Meet Redis LangCache: A Managed Semantic Cache That Cuts LLM API Costs by Up to 90% and Returns Cache Hits Up to 15x Faster
Production LLM applications rarely receive a question nobody has asked before. Support assistants and RAG pipelines field the same intents thousands of times a day, each phrased differently, and most stacks treat every phrasing as a fresh, fully billed request. Redis LangCache is a fully managed sem...
NVIDIA Details BioNeMo Inference Runtime (BioIR): 2.90x Higher Boltz-2 Folding Throughput and 58.5K Residues per GPU-Hour on 8xH100
NVIDIA has detailed BioNeMo Inference Runtime (BioIR), a Python library that accelerates biomolecular structure-prediction models on NVIDIA GPUs while staying in plain PyTorch. In a matched benchmark on 1,000 human dimer targets across 8xH100 GPUs, BioIR-accelerated Boltz-2 delivered 58.5K successfu...