AI Tools news and analysis on Web Pulse: 19497 curated articles tracking the latest AI Tools developments, tools, and research, updated continuously from vetted sources.
Researchers extended PubHealthBench, a public health QA benchmark, into a retrieval-augmented setting and found that hybrid retrieval consistently improves recall and ranking quality. Providing retrieved context substant…
Researchers evaluated the relevance of several RAG metrics by comparing scores from four libraries (Ragas, DeepEval, RAGChecker, Opik) against human evaluators and standard metrics using a question-answering dataset. The…
Researchers introduced AgentLens, a benchmark for evaluating interactive code agents that assesses entire trajectories—including instruction following, tool use, error recovery, and communication—rather than just binary …
A study on text-to-SQL systems found that verification-based signals, such as LLM judges, outperform black-box signals like self-consistency in predicting query correctness, with a two-provider ensemble achieving 0.82 AU…
A new study from arXiv shows that grounding LLM-generated tests in a specification improves code correctness by 38 percentage points over baseline across multiple Claude models, while merely increasing test quantity or c…
Researchers have developed BatteryMat, a three-tier machine-learning-to-density-functional-theory (ML-DFT) workflow for screening lithium-ion cathode materials, as detailed in a July 7, 2026 arXiv preprint. The pipeline …
Researchers propose a new evaluation methodology for LLM-powered software engineering agents, focusing on contamination-awareness, in-the-wild behavior assessment, and trajectory-aware benchmarks to better reflect real-w…
A new 'humanizer' tool released on 20 June by Jie Ding, a machine-learning researcher at the University of Minnesota, can erase signs of AI-written text in papers and grant proposals. While some researchers praise it for…
Omega AI launches a new agent system that automates workflows across Salesforce, Zendesk, and Datadog with 99% accuracy, charging only for completed work and offering a cheaper alternative to Claude Max and ChatGPT Pro.
GitHub announced on July 8, 2026 that enterprises can centrally manage Copilot settings and telemetry controls for VS Code and Copilot CLI through MDM, server-managed settings, or locked local settings files. The update …
Auxilius, a Germany-based AI governance, risk and compliance automation startup, raised EUR 1.3 million in pre-seed funding led by High-Tech Gruenderfonds with participation from Techstars. The company converts enterpris…
A developer discovered that generic ChatGPT answers often stem from insufficient context in user prompts, not model limitations. By explicitly restating subjects, constraints, and desired formats in follow-up questions, …
Thousands of users are abandoning Character.ai in 2026 due to repetitive responses and aggressive filters, seeking alternatives like Polybuzz, Chai, Silly Tavern, and Swerve. A new contender, chatbrat.ai, is gaining trac…
OpenAI launched Patch the Planet on June 22, 2026, deploying AI agents to audit and patch open-source software, finding hundreds of vulnerabilities in the first week including four dnsmasq CVEs, a 23-year-old OpenBSD ker…
A developer outlines the DNS and hosting steps required to deploy an AI-built app to a custom domain, highlighting common pitfalls such as apex vs. www configuration and SSL provisioning failures. The post compares free …
Panora, a French AI software startup for insurance brokers, raised $5 million in seed funding led by Isai and joined by Kima Ventures, 100in, 199 Ventures, and the founders of Pennylane. The company aims to automate admi…
Goldman Sachs Group has become Taiwan's largest foreign brokerage by trading volume in the first half of 2025, rising from 10th place, by expanding coverage of quant funds seeking AI exposure. The bank overtook rivals in…
A 15-year-old Japanese high school student used ChatGPT to develop software that hacked Bandai Namco Filmworks' streaming service, deleting 46,812 subscriber accounts in November 2025. The teenager exploited a security f…
Current AI released v0.1 of its Open Source AI Gap Map, a visualization of over 24,626 open source AI projects across 13+ layers to identify gaps and overinvested areas. The map scores projects on openness, capability, a…
A developer built an interactive atlas of 8.5 million research papers from arXiv, PubMed Central, bioRxiv, and medRxiv, embedding them into a 2D map with LLM-generated summaries, entity links, and an MCP server for AI ag…