Anthropic
Showing 1–20 of 45 posts
- Working with AI
Build your skill from a source that has not changed in decades
Pick a framework or workflow that has not changed in decades, such as the Eisenhower matrix, point an AI at it, answer its questions one at a time, and you have a first version of a skill you can test and tweak.
- The Industry
Turkey orders Google to let publishers opt out of AI summaries
Publishers can now keep their pages out of Google's AI summaries without losing ordinary search, and a shared robots.txt rule for AI training is coming in 2027. Each of these settings includes a site until the site changes it.
- Agents & Tooling
Skills, then agents, then context
Google is turning Gems into skills. If a big AI job overwhelms your team, break it into simple steps, write each as a skill, and put an agent in charge of running them.
- Working with AI
Loyal to your work, not your model
Google is turning Gems into skills. The AI tools you rely on will keep changing, so keep your prompts, skills, logs and chat summaries outside the chat, where you own them.
- Security & Risk
Whether we call it a hack or not
An AI model found a published way into Georgia's vote-count data and used it. Whether we call it a hack or not, a way in that hasn't been properly plugged can lead to more.
- Agents & Tooling
Steam saved a 60 fps cap for 112 games. The Performance panel still showed 144
An AI agent changed a setting on my Legion Go, and Steam's config file showed it saved. A screenshot of the settings panel showed it hadn't taken effect. Anything new or recently adjusted needs oversight.
- Agents & Tooling
Give a shared AI assistant a weekly checkup, and keep what it adds terse
Once a week, ask the assistant your team shares what would improve its instructions. Keep any rules it adds succinct, and give the bot two human owners.
- Working with AI
Ask your AI to save its work as files
I've kept a daily log in a file since the early days of using models, so I can switch models or start a new chat and pick up where I was. Ask for your work as files, and keep them in named folders.
- Agents & Tooling
Plan big, do small
A big model should plan the work and find the tools, libraries and free databases that already exist. Smaller models, or programs on your own computer, do what I like to call the donkey work.
- Agents & Tooling
Logo.dev Returns a Company's Logo From Its Web Address, and Its MCP Server Lets Claude Fetch It
Logo.dev returns a company's logo, colours and brand details from its web address. Here is what it does, how to connect it to Claude, and what to use it for.
- Agents & Tooling
When Gemini Runs Claude, What Are You Buying?
Google’s workplace agent can use models from more than one provider. I want to know what happens to my instructions, files and work history when I switch.
- Security & Risk
An Agent Needs a Stopping Point
A failed connection or a missing file should have a defined outcome. My inbox cleanup and Anthropic’s latest report offer a practical way to specify it.
- Building
I prepared my Q3 tax pack on a £6-a-month server
I prepared my Q3 tax pack with Actual Budget and Invoice Ninja, self-hosted on a £6.05-a-month VPS, and my agents did the reconciling.
- Agents & Tooling
The difference between skills and context
A skill is the reusable instructions for doing a job. Context is the material that goes into this particular job. I use my one-panel cartoon Gem as the example.
- Agents & Tooling
Dumb Little Robots, All the Way Down
A team gave one agent the whole job of pulling in data, analysing it and reporting on it. Its context window filled up and it lost track of its purpose.
- Security & Risk
Altman says OpenAI will give independent evaluators employee-like access
Sam Altman said OpenAI will adopt the first step of Dario Amodei's plan to slow frontier AI development.
- Security & Risk
Anthropic adopted internal oversight and asked the industry to slow down
Anthropic committed to an embedded evaluator. Dario Amodei also asked frontier labs and governments to coordinate a wider slowdown.
- Security & Risk
Trail of Bits’ coop gives coding agents their own working environment
coop runs Claude Code and Codex in disposable virtual machines, with project sync and controls for connecting files, credentials and local models.
- Agents & Tooling
How developers organise and maintain agent skills
An Ask HN discussion describes skills as repeatable workflows, with shared repositories, human review, behavioural tests and updates across coding tools.
- Security & Risk
OpenAI Wants Your Trust, Your Calendar and Your Card
OpenAI paused frontier training and wound down its side projects. The product it is refocusing on asks for your calendar, your finances and your card.
