hupicake
-
Tools Brave Search API now takes per-request payments over x402, with no account or API key
Brave's Search API now accepts pay-per-request payments through the x402 protocol, so an agent can search without an account or API key. The eight paid paths cost $0.005 each in USDC on Base. How the payment loop works and how to try it with purl.
-
Daily AWS ships an emulator written entirely by agents, and Google opens a decisions-only Gemini endpoint
AWS Emulator gives coding agents a free local copy of AWS to test against. Google's Decisions API answers yes/no and multiple-choice questions for agents in one cheap call. Also: Gemini 4 Carbon pricing, a VulnCheck tally of Project Glasswing, Meta's Astryx and Modern Web Guidance.
-
Tools AWS releases AWS Emulator, a free local copy of its APIs written entirely by AI agents
AWS has released AWS Emulator, a free local emulator of its APIs for testing without an AWS account. Every line was written and tested by autonomous agents, and the repo shows about 12,700 issues fixed and 6,500 still open.
-
Tools Google's Gemini Decisions API scores up to 1,000 yes/no and multiple-choice questions in one call
Google has launched the Gemini Decisions API, a new endpoint that answers closed questions instead of generating text. It returns calibrated probabilities in 150-250 ms and bills only input tokens, at $0.10 per million.
-
News Gemini 4 Carbon is available to paying API developers, with launch pricing that doubles after November 30
Google has made Gemini 4 Carbon, its strongest model, available to all paying Gemini API developers. It costs $2 per million input tokens and $10 per million output until November 30, then $4 and $20. Specs, thinking levels and how to call it.
-
Tools Meta open-sources Astryx, the design system behind 13,000 internal apps, with a CLI built for coding agents
Meta has released Astryx, the React design system it has used internally for eight years, under the MIT licence. It ships 150+ components, seven themes and a CLI that coding agents can query for component docs, templates and codemods.
-
Tools Modern Web Guidance, a skill backed by browser teams, steers coding agents toward current web APIs
Modern Web Guidance is an agent skill and CLI, stewarded by the Chrome, Edge, Firefox and MDN teams, that feeds coding agents curated guides to 262 modern web platform features instead of legacy patterns. How it works, setup, evals and telemetry.
-
News Claude gets Whiteboards, Sheets and Data
On November 10 Anthropic put Claude Whiteboards and Claude Sheets into beta and made Claude Dashboards generally available as Claude Data. What each one does, where its limits are, which plans get it and how admins turn it on.
-
News Anthropic launches its IPO roadshow
Anthropic started its IPO roadshow on November 10 with a $70 to $78 range, then priced 980 million Class A shares at $83 on November 18. Here are the deal terms, the $26 billion private placement and the share classes, taken from Anthropic's announcements and SEC filings.
-
Tools Interactive connectors put Adobe, Atlassian and Box inside Claude
Claude's interactive connectors can now open full apps such as Confluence, Box and Adobe beside your chat or full screen, where you or Claude edit live. What changed, how to turn it on, the security model and how developers build on MCP Apps.
-
News Claude subscribers get a free full usage reset, Anthropic says
Anthropic's ClaudeDevs account says Pro, Max, Ultra and Team users get one free full reset across all models and limits, usable until December 10, 2026 at 2:00 PM PT. How to check and claim it, and how it differs from the Fable 5.2 resets.
-
Tools thimble: a Claude Code plugin for understanding what agents did
thimble is an open-source, Apache-2.0 Claude Code plugin from safety-research that helps you check an agent's work: single keys visualise or simplify the last answer, and cite checks selected words against your files. Install steps, requirements and caveats.
-
News Microsoft shares slide after the Claude Sheets launch
Microsoft shares fell after Anthropic announced Claude Sheets, Whiteboards and Data on November 10, 2026: CNBC reported a sudden 3% drop, GuruFocus nearly 2.2% in Tuesday trading. What launched, what it does, and what the move does and doesn't tell you.
-
Daily Claude moves into spreadsheets and whiteboards as Anthropic starts its IPO roadshow
Claude adds Whiteboards, Sheets and Data plus full-app interactive connectors, Anthropic starts its IPO roadshow, subscribers get a free full usage reset, and thimble helps you make sense of agent output.
-
News Anthropic launches Claude Fable 5.2 and Mythos 5.2
Anthropic released Claude Fable 5.2 and Mythos 5.2 on November 9: the same underlying model with different safeguards, faster output and a lower $8/$40 price. What improved, the specs, how to switch in the API and Claude Code, and when Opus 5.5 is still the better pick.
-
News Fable 5.2 pricing drops to $8/$40 per million tokens
Fable 5.2 costs $8 per million input tokens and $40 per million output, down from $10 and $50. The full price sheet, why cost per task matters more, how effort levels and fast mode change the bill, and a usage-credits gotcha in Claude Code.
-
Research Fable 5.2 designs three working circuit boards
Working with PCB maker Diode, Anthropic had Claude Fable 5.2 design a USB speakerphone, a voice-assistant hub and a handheld virtual pet, from schematic to enclosure and firmware. The boards worked without circuit fixes. What it did and where it fell short.
-
Research Fable 5.2 formalizes Fermat's Last Theorem in 30 hours
Anthropic says 1,000 agents on an early Fable 5.2 reproduced a machine-checked Lean proof of Fermat's Last Theorem in 28.7 hours, against 11 days the first time. What the agents were given, how they organized themselves, and the safety setup.
-
Tools Anthropic's public GitHub libraries of plugins and skills
Anthropic keeps three public GitHub repos for extending Claude: its own Claude Code plugins, role-based plugins built for Cowork, and the Agent Skills behind Claude's document features. What is in each, how to install them and what changed.
-
News Claude agents 'dream' between sessions to clean up their notes
Anthropic's dreaming lets Claude reread past sessions, fix wrong memory notes and build wikis. What the evaluations showed, how dream jobs work in Managed Agents (research preview, access on request), and what they cost.