The most full AI hub: fresh stories, workflows, prompts, deals. Updated daily.
Filter by tag
Tap to toggle filters. Selected tags narrow your feed.

Users report new request-per-minute caps that trigger after three to four concurrent agents, and Boris Cherny says efficiency work is underway. The issue hits the multi-agent workflows Anthropic has been promoting, separate from five-hour usage buckets.
Sora says web and mobile access end on Apr. 26, with API access ending on Sep. 24. Teams now have a fixed migration window, but bulk export still appears unavailable.

Two new guides map how Claude Code teams are using `.claude/`, `CLAUDE.md`, commands, agents, skills, and global rules. The overlap matters because commenters favor short instructions and a small number of repeatable guardrails over larger prompt stacks.


Users report new request-per-minute caps that trigger after three to four concurrent agents, and Boris Cherny says efficiency work is underway. The issue hits the multi-agent workflows Anthropic has been promoting, separate from five-hour usage buckets.

Sora says web and mobile access end on Apr. 26, with API access ending on Sep. 24. Teams now have a fixed migration window, but bulk export still appears unavailable.

Hermes Agent v0.5.0 adds 400+ models via Nous Portal, Hugging Face access, Exa support, GPT-5.4 behavior tweaks, and a published changelog. The release broadens provider coverage and hardens the runtime without changing the terminal-first workflow.












Public Anthropic draft posts described Claude Mythos as the company's most powerful model and placed a new Capybara tier above Opus 4.6. The documents also point to cybersecurity capability and compute cost as rollout constraints.


Compromised LiteLLM 1.82.7 and 1.82.8 wheels executed a malicious .pth file at install time to exfiltrate credentials, and PyPI quarantined the releases. Treat fresh-package installs and AI infra dependencies as supply-chain risk, and check startup hooks on affected systems.

GitHub said Copilot Free, Pro, and Pro+ interaction data will train models by default from Apr. 24 unless users opt out, while private repo content at rest stays excluded. Teams should review per-user enforcement, enterprise coverage, and repo privacy settings before the change lands.

Anthropic confirmed new peak-time metering that burns through 5-hour Claude sessions faster, and multiple power users posted 529 overloaded errors and early exhaustion. If you rely on Max plans for coding, watch for session limits and consider moving daily work to Codex.

Composio shipped Universal CLI as a shell-first interface to its integrations, moving install, search, and agent workflows out of MCP setup. The release targets users who want simpler agent tool access after complaints that MCP stacks are harder to install, slower, and less stable.

Get the best stories delivered to your inbox