AI Research

Automating coherent long-form video generation

Generative AI

AI Agents Are Now Operating Enterprise Networks. Trust Sets the Limits.

AI agents already act in production networks at 51% of surveyed organizations. Cisco and Omdia’s research explores how far companies will extend that authority and which controls they expect.

Claude Opus 5.5 Broke Our GPT-6 Benchmark

We tried to benchmark Claude Opus 5.5 against GPT-6 Sol. Then Opus kept building, judging, fixing, and iterating until the benchmark itself stopped making sense.

Meta’s Big AI Bet Now Fits on Your Keychain

Meta Connect put Muse on a keychain, promised it for AI glasses, and gave its personal agent voice, email, and computer-use ambitions. Here’s why I’m excited.

True Positive Weekly #179

The most important artificial intelligence and machine learning news and articles

😺 LIVE IN 5: GPT-6 Sol vs. Claude Opus 5.5

Who Made Space Bunny? A MiniMax Clue Sharpens the Mystery

Space Bunny is the latest free mystery model on OpenCode and OpenRouter. A new fingerprint points toward MiniMax, while Big Pickle’s 11-month run shows how long an AI model can stay behind an alias.

How to Maximize Your Coding Agent Subscriptions

Get more out of your coding agent subscriptions The post How to Maximize Your Coding Agent Subscriptions appeared first on Towards Data Science.

Beyond RAGs: Building Actually Truthful AI Harnesses

Retrieval is not evidence. How to build AI that proves its own claims. The post Beyond RAGs: Building Actually Truthful AI Harnesses appeared first on Towards Data Science.

Adobe Wants Its Tools Wherever Your Next Project Starts

Adobe’s latest updates put Photoshop and other creative tools on a path to Gemini, add Acrobat and hands-on editing to Claude, and bring Premiere to Android. The common thread: Adobe wants its tools available wherever a…

Towards Spec-Driven Test Automation: Part 1

Why a green test suite can mean nothing The post Towards Spec-Driven Test Automation: Part 1 appeared first on Towards Data Science.

Jensen Huang’s AI Safety Rule: If You Can’t Evaluate It, Don’t Ship It

Jensen Huang says AI labs should treat safety like engineering: evaluate, verify, contain, and don’t ship systems they can’t control. The deeper problem may be the industry’s scale-at-all-costs feedback loop.

When the Correct Answer Is Nothing, What Does Your Pipeline Return?

The reliability mechanisms we add to LLM pipelines are often the ones that make them confidently wrong. The post When the Correct Answer Is Nothing, What Does Your Pipeline Return? appeared first on Towards Data Science.

😺 What 950 Claude agents found

Sparse-Observation Atmospheric Thermal Forecasting with Physics-Informed Neural Networks for Climate-Aware Digital Twins

arXiv:2609.27290v1 Announce Type: new Abstract: Short-horizon forecasts of atmospheric temperature are needed to support climate-aware digital-twin systems, but such forecasts must be produced where thermal observations…

Evaluating ADC-only deep learning pipelines for breast cancer detection and segmentation using standalone diffusion-weighted MRI

arXiv:2609.27815v1 Announce Type: cross Abstract: Dynamic contrast-enhanced (DCE) imaging is the gold standard technique for the detection and characterization of breast cancer using magnetic resonance imaging (MRI).…

InterPol: De-anonymizing LM Arena via Interpolated Preference Learning

arXiv:2603.15220v2 Announce Type: replace Abstract: Strict anonymity of model responses is a key for the reliability of voting-based leaderboards, such as LM Arena. While prior studies have attempted to compromise this…

PotARCin: Multi-Dimensional Evaluation of Skill Acquisition in Abstract Reasoning Tasks

arXiv:2609.27288v1 Announce Type: new Abstract: The Abstraction and Reasoning Corpus (ARC) has become a prominent benchmark for evaluating general abstract reasoning and fluid intelligence in AI models. Yet standard ARC…

Not What You Meant: Can LLMs Follow a Specified Negation Semantics?

arXiv:2609.27517v1 Announce Type: new Abstract: Negation does not carry a uniform interpretation across domains. In legal, regulatory, and medical reasoning, the intended interpretation depends on the reading in force…

Just-in-Time Memory: Learning to Curate Task-Adaptive Memory for LLM Agents

arXiv:2609.27334v1 Announce Type: new Abstract: Agentic memory systems reuse past experience to improve future performance, yet most existing designs curate memory at write time: once a task is completed, its trajectory…