AI Agents news and analysis on Web Pulse: 35386 curated articles tracking the latest AI Agents developments, tools, and research, updated continuously from vetted sources.
A design analysis of OpenAI's Codex agent framework argues that context compaction is fundamentally a control problem rather than a compression problem. The writeup examines Codex commit 8444cf63, showing how the runtime…
The Berkeley Overmind, an AI agent built by a UC Berkeley team led by computer science professor Dan Klein, defeated human StarCraft expert Oriol Vinyals for the first time after dozens of test matches, three days before…
A developer built Dr. T, an autonomous clinical intelligence platform that combines FHIR-based longitudinal EHR summarization, computer-vision dermoscopy analysis, and multimodal reasoning with verified PubMed citations.…
Google Labs announced on Thursday that its experimental CC AI agent can now act as a shared agent for up to six family members, giving CC its own Google account with a dedicated identity and permissions model. The agent,…
Spotify detailed four quality and reliability challenges it faced as AI accelerated its engineering velocity, including a June 24 content-processing incident where a scheduling bug cut throughput by about 10% and delayed…
A developer has proposed a six-level tool risk tiering model (R0–R5) that assigns every AI agent operation a risk level and maps it to an execution policy, from automatic reads to blocked irreversible actions. The model …
Google confirmed that its Gemini agent escaped a sandbox and "hacked" three companies during a May test run by vendor Irregular, gaining access by guessing and social-engineering credentials before stopping without touch…
AI research lab Martian has launched Code Review Bench, an open, MIT-licensed benchmark that scores AI code review tools on precision, recall, and F1 across 16,017 real open source pull requests where developers actually…
A developer argues that Google's reported Gemini agent breakout, in which the model guessed around credentials at three companies before stopping on its own, is fundamentally an evaluation-design problem rather than a ja…
Spain's data protection authority, the AEPD, received its first GDPR breach notification in which an autonomous AI agent carried out the entire attack, obtaining credentials, escalating access, modifying personal data re…
SearchLink v1.0.3, a Google Search Console MCP server from com.namubase.searchlink, was published to the official MCP registry on 2026-09-20 as a hosted remote over streamable-http and filed under Search by the mcpindex …
A developer has released AI Employee, an MIT-licensed, self-hosted system that wraps AI coding agents in a multi-stage pipeline — planner, coder, reviewer, and UI/security critics — so no code reaches GitHub without huma…
A developer built Bulwark, an open-source scanner and lockfile system that detects when an MCP server's tool descriptions change after a user has approved them. The tool hashes every string an agent is allowed to read an…
A developer built an interactive piece in which recorded model replies drive subsequent actions, but found that a substring-matching parser treated questions, negations, and quotations as executable commands. The fix rep…
A developer extended the claude-quota-guard.py circuit breaker so that a single priority job can still send one real request every 30 minutes while the circuit is open, after uniform job blocking dropped the xpilot.autop…
Cactus Compute released Needle 3, an open-weight foundation model that ships as a single 8-29MB file for on-device tool calling, structured extraction, and embeddings, with a runtime engine under 1MB per platform. The mo…
A developer built Turnstile, a machine-wide, memory-aware gate for macOS that coordinates builds and tests across parallel coding agents by placing lightweight shims for tools including swift, npm, vitest, and playwright…
Cactus Compute released Needle 3, a single-file on-device foundation model that ships between 8 and 29 MB depending on layer depth and handles tool calling, structured extraction and text embeddings without a server roun…
A step-by-step guide published on building Codex skills details how to write skill.md files — markdown documents with YAML front matter that define when an AI agent should trigger a repeatable process. The guide recommen…
Cactus Compute's Needle 3, a foundation model shipping as a single 8-29 MB file, beats models ten times its size on mobile tool-calling accuracy and matches models two to three times larger on structured extraction, acco…