"Anthropic have added one of the most important missing features to Claude Artifacts: apps built as artifacts now have the ability to run their own prompts against Claude via a new API.

Claude Artifacts are web apps that run in a strictly controlled browser sandbox: their access to features like localStorage or the ability to access external APIs via fetch() calls is restricted by CSP headers and the <iframe sandbox="..." mechanism.

The new window.claude.complete() method opens a hole that allows prompts composed by the JavaScript artifact application to be run against Claude.

As before, you can publish apps built using artifacts such that anyone can see them. The moment your app tries to execute a prompt the current user will be required to sign into their own Anthropic account so that the prompt can be billed against them, and not against you.

I'm amused that Anthropic turned "we added a window.claude.complete() function to Artifacts" into what looks like a major new product launch, but I can't say it's bad marketing for them to do that!

As always, the crucial details about how this all works are tucked away in tool descriptions in the system prompt. Thankfully this one was easy to leak. Here's the full set of instructions, which start like this:"

https://simonwillison.net/2025/Jun/25/ai-powered-apps-with-claude/

#AI #GenerativeAI #Claude #LLMs #Chatbots #ClaudeArtifacts #API

MIT’s New AI Model Predicts Human Behavior With Uncanny Accuracy

Researchers at MIT developed a way to model the behavior of an agent, whether human or machine, that accounts for the unknown computational constraints that may hamper the agent’s problem-solving abilities.

#MIT #ArtificialIntelligence #AI #modeling #humanbehavior #psychology #technology #tech

https://scitechdaily.com/mits-new-ai-model-predicts-human-behavior-with-uncanny-accuracy/

Q: Why is Donald Trump suddenly selling $60 bibles?

A: It enables churches to funnel money to him without violating the (US law) ban on political campaigning by churches—it's a form of money laundering, in other words.

The #AI sidekick that tests its own #code and iterates until it works.

Otto Engineer - Autonomous AI software engineer that runs in the browser
Otto Engineer is an autonomous agent that takes AI-assisted coding to the next level.

Otto checks its work and iterates - Otto executes its code and tests it to make sure it works. If there are errors, it will keep iterating until the code works 🦾

Otto executes its code safely in isolation
https://otto.engineer/

#nodejs #javascript

👏🏼 👉🏼Via Democracy Docket:

BREAKING: #NorthCarolina court strikes down power-grab law that transfers the ability to appoint members to the state board of elections from Gov. Roy Cooper (D) to the Republican-controlled state legislature. #legal