AI
Artificial intelligence: LLMs, agents, diffusion, vision, NLP and the latest from top labs.
593 published articles
Per-Call Routing's Blind Spot in Agentic AI
For agentic AI, per-call routing is the blind spot. TRACE-Router has a fix.
A new routing framework, TRACE-Router, tackles the mismatch between per-call LLM routers and task-level success metrics in agentic AI, gaining up to 8 accuracy points and 36% lower latency.
2026-08-01
Cybersecurity
Devin-powered service promises to clear 80% of security backlogs
LTM and Cognition's Devin-powered remediation service promises to clear 80% of CVE backlogs at 30% lower cost. But the partnership targets only high-confidence fixes first, and every patch needs human sign-off. We examine whether AI can really scale vulnerability management.
2026-08-01
Ecosystem play
Grok 4.5's biggest news might be how it was built
xAI's Grok 4.5 is now on grok.com, X, iOS, Android, and inside Microsoft 365, Google Workspace, GitHub Copilot, and Cursor. The model, built with agent-constructed training data, leads the SWE Marathon benchmark and introduces a voice upgrade.
2026-08-01
Zero-shot AI for industrial root cause analysis
AgentRCA: zero-shot root cause analysis that explains its own reasoning
A
2026-08-01
AI & Robotics
Training surgical robots just got faster: Nvidia's Cosmos-H-Dreams runs at 160 fps
Nvidia's Cosmos-H-Dreams turns surgical simulation into an interactive, real-time experience. Running at 160 fps on a single GPU, it lets surgeons, trainees, and AI policies practice inside a closed loop of generated video without needing a physical robot.
2026-08-01
Graph Foundation Models
Zero-shot transfer on graphs has a multimodal blind spot. CHARM offers a fix
CHARM replaces isolated node features with structured graph contexts that capture multimodal semantics and cross-modal relations. By mapping domain-specific patterns to shared high-level concepts, the model achieves zero-shot transfer across graphs with text, images, and other modalities.
2026-08-01
Enterprise AI
Anthropic's Claude finds its enterprise bridge: 30,000 Cognizant engineers
As AI capability outpaces enterprise adoption, Cognizant expands its Anthropic partnership, training 30,000 staff on Claude and delivering measurable productivity gains like 40% faster contract reviews and eight-hour weekly savings for underwriters. The deal signals a strategy to embed frontier AI through existing enterprise systems.
2026-08-01
AI Integrity
The AI Pipeline Has Three Silent Leaks, and Every Fix Makes One of Them Worse
A comment-spam poisoning study, a paper showing AI detectors can backfire, and a fraud-detection model caught exploiting label leakage all describe the same underlying failure: proxy measures in AI pipelines get gamed the moment they become load-bearing, and fixing one doesn't fix the pattern.
2026-07-31
Developer Tools
Nobody Shipped a Breakthrough This Week. That's the Actual News.
xAI's bug-fix release, Apple opening Xcode to rival AI models, and Bruno's bring-your-own-key overhaul all skip flashy new features for reliability and data trust. Together they signal the AI developer tools market shifting from a feature race to a trust race.
2026-07-31
Deep Research AI
BAAI's new research agent doesn't just search longer, it checks its own homework
BAAI's AREX agents use a recursive self-improvement loop that compresses long research histories, enabling efficient verification-driven refinement. Trained with a novel long-horizon RL recipe, they outperform comparable baselines on BrowseComp, DeepSearchQA, and HLE.
2026-07-31
3D Reasoning
SceneActBench: Why even the best VLMs fail at 3D action
SceneActBench tests eleven VLM configurations on five 3D tasks in a unified agent loop. Overall scores range from 38.6 to 50.2, with no model performing consistently. The benchmark exposes a blind spot in vision-language agents: acting on full scenes, not just describing them.
2026-07-31
Automated Playtesting
Candy Crush just proved grid-based AI is the wrong approach for complex games
King Digital researchers compared GAT, BERT, and CNN models for automated playtesting in Candy Crush Saga. GAT models matched or outperformed CNNs in move prediction and difficulty estimation, especially on hard levels, while also handling new game mechanics without feature engineering.
2026-07-31