Nvidia just showed that the harness, not the AI model, is now the real hero
Nvidia research shows that AI agents can perform well, and not go off the deep end, through fine-tuning, even if the AI model isn't that great at the task.
Nvidia published research showing that the software scaffolding around an AI model, called a harness, matters more than the model itself when asking AI to complete long-horizon tasks that require stringing many decisions together over time. In their tests, Claude Opus 5 scored 30 percent on an interactive reasoning benchmark without a custom harness but achieved a 100 percent score when given a harness that included a supervising agent component to redirect the model when it gets stuck. This finding aligns with earlier research from other companies indicating that harness choice significantly impacts both AI performance and costs, meaning that control over the tools and rules surrounding a model can be more important than simply selecting a more advanced model. The research supports the argument for open harnesses that give users greater control over how AI systems operate.
One short email a day with the stories that matter. Free. Unsubscribe with one click.
Want to go deeper than the news? Explore live, cohort-based AI courses taught by practitioners.
Browse AI courses on Maven
Google DeepMind just mathematically verified key parts of Signal
Google DeepMind researchers used agentic AI to mathematically prove, or “formally verify,” a number of the Signal protocol’s key cryptographic guarantees—a landmark development for the widely used cryptography and AI itself. Conducted as a sort of proof-of-concept project in just four weeks, the work is significant in two ways. It serves as further independent validation of the cryptography that protects massive quantities of the world's communications on platforms like the Signal app, Google Me
Baidu’s ERNIE Evolve Automated Research System Beats NanoChat and NanoGPT Records
Baidu has just released ERNIE Evolve, an automated research system that improves AI training and inference code. Given a repository, an objective and evaluation criteria, it picks research directions, edits code and runs experiments. Only changes that pass a hidden evaluator and a separate reviewer are kept. Baidu team tested the ERNIE Evolve automated research system on three public benchmarks. It then optimized inference for ERNIE-5.5-Flash, still in development. TL;DR Size: It is an
AI coding agents still need human cleanup on nearly three out of four tasks in a real-world test
Alibaba's new coding-agent benchmark, Co-Design Bench, tests AI agents on real user requests that already tripped them up in practice. Even GPT-6 Astra, the top performer, fully solves only 26.4 percent of tasks. On older benchmarks, the same models score above 99 percent. The article AI coding agents still need human cleanup on nearly three out of four tasks in a real-world test appeared first on The Decoder.
The gap between open and closed AI models in cyber capabilities keeps shrinking
In the Vals AI benchmark, OpenAI's GPT-6 Sol Daybreak hits 80.8 percent of attack objectives in simulated corporate networks. Worse, the open-weight model DeepSeek V4.1 Flash reaches 72.8 percent at a tenth of the cost. Because open models can no longer be restricted, analysts say the window for defenders is shrinking fast. The article The gap between open and closed AI models in cyber capabilities keeps shrinking appeared first on The Decoder.
Nine AI agents tried autonomous research on open questions from US national labs and none passed the experts' bar
The "Into the Unknown" benchmark tasks nine AI agents with tackling open research questions from U.S. national laboratories. None of the 135 submissions meets all requirements. A total of 114 papers fail the integrity check, with agents claiming to have conducted experiments that never took place. GPT-6 Astra performs best but still doesn't meet the experts' standards. The article Nine AI agents tried autonomous research on open questions from US national labs and none passed the expert
Ripple-65B Preview delivers strong agentic coding results as a fully Apache 2.0 open US model
Ricursive Intelligence is releasing Ripple-65B Preview, a 65-billion-parameter open-weight language model that the company says achieves the top score among open-source U.S. models on the TerminalBench 2.1 coding benchmark at a total R&D cost of $32 million. On other benchmarks, however, Ripple falls behind the likewise newly released western open model Inkling 2 Small. The article Ripple-65B Preview delivers strong agentic coding results as a fully Apache 2.0 open US model appeare