Tag: AI
-
System Prompts – Claude Docs
See updates to the core system prompts on [Claude.ai](https://www.claude.ai) and the Claude [iOS](http://anthropic.com/ios) and [Android](http://anthropic.com/android) apps. — Read on platform.claude.com/docs/en/release-notes/system-prompts
-
Claude’s new constitution \ Anthropic
A new approach to a foundational document that expresses and shapes who Claude is — Read on www.anthropic.com/news/claude-new-constitution
-
10 things I learned from burning myself out with AI coding agents – Ars Technica
with LLMs, context is everything, and in language, context changes meaning. Take the word “bank” and add the words “river” or “central” in front of it, and see how the meaning changes. In a way, words act as addresses that unlock the semantic relationships encoded in a neural network. So if you put “checkerboard” and…
-
Claude Code and Graphic Design
I asked Claude to tell me what it was good and bad at: What I’m Bad At (Don’t Ask Me) 1. Graphic Design / Visual Aesthetics My SVG logo attempt was a perfect example – technically valid SVG, but visually uninspiring and generic. The “wood grain” is just a gradient that looks nothing like actual…
-
A quote from Boaz Barak, Gabriel Wu, Jeremy Chen and Manas Joglekar
One way to think of confessions is that we are giving the model access to an “anonymous tip line” where it can turn itself in by presenting incriminating evidence of misbehavior. But unlike real-world tip lines, if the model acted badly in the original task, it can collect the reward for turning itself in while…
-
Love Machines by James Muldoon
The risk here is clear enough: the more emotionally involved we become with AI chatbots, the greater our loneliness may grow, as the muscles required to navigate the frictions of human relationships wither. https://www.theguardian.com/books/2026/jan/13/love-machines-by-james-muldoon-review-the-risks-and-rewards-of-getting-intimate-with-ai
-
Using generative AI to learn is like Odysseus untying himself from the mast
AI can help with long-run learning if you first do the work yourself. The study evaluates tutoring program that activates AI assistance only after a user first submits a solution. I don’t know if that’s the right approach, but it seems like a good start. Learning is hard work. And there is now lots of…
-
First impressions of Claude Cowork, Anthropic’s general agent
The interface for Cowork is a new tab in the Claude desktop app, called Cowork. It sits next to the existing Chat and Code tabs. It looks very similar to the desktop interface for regular Claude Code. You start with a prompt, optionally attaching a folder of files. It then starts work. I tried it…
-
Coding With Claude Week 2: End of the Honeymoon?
This week, Claude helped me bring my son onboard to collaborate on our contract whist scoreboard and that worked very well. Then I began a new project – a link management system with rich categorizing, tagging and drag and drop support. I wanted to test Clause on more complex graphical interactions (and make something that…
-
How Grok’s nudification tool went viral
As people slowly started to understand the full potential of the tool, the increasingly degrading images of the early days were quickly superseded. Since the end of last week, users have asked for the bikinis to be decorated with swastikas – or asked for white, semen-like liquid to be added to the women’s bodies. Pictures…