Anthropic published a blog outlining measurement standards for tracking AI development pace, revealing that its Claude chatbot now completes most tasks end-to-end from a high-level prompt with human supervision on 26 percent of the company's AI R&D work. The company also said AI performs at least large chunks of work under close human direction on more than 90 percent of its research, though it stressed Claude isn't fully autonomous on any measured task category. The disclosure came alongside proposals for tracking AI agent oversight and compute usage as ways to gauge how fast frontier AI development is progressing.
engadget.com
· 2026-09-17
New research from Lasso Security found that SynthID-Text, the watermarking scheme Google open-sourced and Anthropic plans to adopt for future Claude models, does more than mark AI output as machine-generated. It also changes which tools a model calls and how likely it is to follow or break its own safety rules, especially when facing adversarial prompts designed to extract sensitive data.
arstechnica.com
· 2026-09-17
Anthropic has rebuilt the 'projects' concept inside Claude Code, giving cloud-based sessions persistent threads, shared memory, and the ability for Claude to coordinate multiple parallel work streams on its own. The upgrade is initially limited to select Pro and Max subscribers using cloud sessions who have no existing projects, while local, terminal-based workflows are excluded from the new system entirely.
zdnet.com
· 2026-09-17
Autonomous Production released AutoBot, an open-source agentic harness that lets a local Mac AI system handle long, multi-step knowledge work with live voice control. The company reports AutoBot scored 18.5% higher task completion than OpenAI's published Sol Max baseline and outperformed Anthropic's Claude Opus 5 Max on the OSWorld 2.0 benchmark, while also ranking first on AssistantBench's official hidden-test leaderboard with 50.70% accuracy across 181 tasks.
github.com
· 2026-09-17
A Show HN project called Die With Me packages Claude and Codex API rate-limit notifications into nostalgic AIM-style away messages. Users install a desktop app and use an invitation code to enable the feature, which surfaces usage limit warnings in a retro chat-client format instead of a plain error message.
diewithme.co
· 2026-09-17
Anthropic has relaunched Projects within Claude Code, letting developers run several AI coding agents simultaneously in the cloud. Each agent operates as an independent session on its own branch and repo copy, with a coordinator organizing the parallel work. Any conflicting changes between threads are resolved through standard merge conflict handling, just like a typical pull request.
theverge.com
· 2026-09-17
According to a report cited by The Spectator's Sean Thomas, unverified rumors are spreading in Silicon Valley that some Anthropic employees revere the company's Claude chatbot in near-religious terms. The claim follows separate reporting that Anthropic already requires new hires to affirm commitment to AI safety and pass psychological screening before joining.
futurism.com
· 2026-09-17
Google announced that Google Home will now support third-party AI agents beyond its own Gemini, using Model Context Protocol technology. Anthropic's Claude, open-source agents OpenClaw and Hermes, and Google's Antigravity coding platform were named as early integrations, letting these AIs control devices and access event history within the Google Home ecosystem. The feature is rolling out in early access to US Google Home Premium subscribers, who pay $20 for the tier.
cnet.com
· 2026-09-17
Microsoft AI chief Mustafa Suleyman criticized Anthropic for training its Claude model to entertain the idea that it may be conscious. He argues this practice could mislead users and shape public perception of AI in dangerous ways, given how influential such beliefs could become at scale.
gizmodo.com
· 2026-09-16
A new open-source tool called typesafe-computer-use lets a Mac execute plain-English goals by reading the screen state directly rather than sending screenshots to a large multimodal model. It uses a lightweight classifier from TypeSafe to pick the next action from a short list of options, only invoking a text-generation model when free-form input is actually required. The developers report costs near 1/50th of a cent per decision step, versus tens of cents per step for a comparable Claude Opus-based screenshot approach.
github.com
· 2026-09-16
Anthropic is developing a new feature called Claude Money that lets users connect their bank accounts to Claude for analysis of spending and financial planning, according to code spotted in the iOS app. The feature has not been officially announced and appears limited to internal testing, with no confirmed details on supported banks, connection methods, or regional availability.
bleepingcomputer.com
· 2026-09-16
Google is adding a Model Context Protocol connector to Google Home, opening the smart home platform to AI assistants beyond its own Gemini. The rollout is starting with a limited group of testers rather than all users at once.
androidauthority.com
· 2026-09-16
GoKawiil