Tag: claude
-
Anthropic is building a PaaS.
Anthropic is building a PaaS. They’ve got isolated VM’s/containers, they’ve thought out support languages for the major languages. You can even write code in the browser…with the AI. And it checks your stuff into GitHub? Plus, of course, it runs your code for you, at least with Claude Skills. 🔗 Claude Code for web –…
-
“The context window is a public good.” Skill authoring best practices,Claude Docs
-
Generate and execute code in Claude’s web app, also pull from GitHub and package managers. What else can you have it do and install in the containers(?) it’s running?
Generate and execute code in Claude’s web app, also pull from GitHub and package managers. What else can you have it do and install in the containers(?) it’s running? 🔗 Claude Sonnet 4.5 is probably the “best coding model in the world” (at least for now)
-
Anthropic lets Claude remember previous interactions to streamline work – Including, and using, past chats in your current chat. Always a great, helpful feature.
-
Invisible to the robots
In my searches/research, analysts like Gartner, IDC, and Forrester are invisible to ChatGTP, Claude, etc. The robots will find the reports licensed by vendors – I’m guessing only if they don’t require leadgen. The analysts should probably start publishing some juicy abstracts with just enough numbers, analysis, and advice to get into the training data…
-
“Music for Claude Coding.” What I think about when I think about Claude Code
-
10 Months into AI Agents : Which Are Used Most? – Feels like it’s primarily about supporting programming, not doing things in apps. // Not sure about the methodology and source for this chart, tho.
-
How I Use Claude – “Claude is really good at helping here, mostly because thinking quickly saturates: when you’ve thought about a problem for five minutes, you’ve had all the thoughts you’re gonna have, and it’s time to talk to someone else. Claude lets me sample fresh perspectives and possible actions I had not thought…
-
A consumption basket approach to measuring AI progress – “In contrast, actual human users typically deploy AIs to help them with relatively easy problems. They use AIs for (standard) legal advice, to help with the homework, to plot travel plans, to help modify a recipe, as a therapist or advisor, and so on. You could…
-
A think tool
Giving AI an inner-voice with Model Context Protocol I separated out a “think tool” from my agentic D&D project this week. The think tool is stupidly simple: all it does it echo back whatever the AI sends it. The original write-up from Anthropic makes it seems a little more mystical, but it doesn’t take long…
-
Is this your brain on ChatGPT? –
-
Edisum: Summarizing and Explaining Wikipedia Edits at Scale – A prompt for summarizing edits made to text.
-
MCP Is RSS for AI: More Use Cases for Model Context Protocol – I like this: “I’m inclined to think of MCP as RSS for AI.” // Once prompts are used as intended – to be user initiated activity in the UI, we’ll see if things evolve. Think of an MCP prompt as adding a…
-
Agents are models using tools in a loop – “Agents are models using tools in a loop,” Anthropic’s Hannah Moran.
-
Spy on the DM with Model Context Protocol Servers in Java – Solo roleplaying D&D with agentic AI, #02
Not only can you give more direction to the AI when you’re playing solo D&D with it, you can start to understand how it thinks. I walk through how to use MCP Server tools to enhance solo roleplaying with Claude (and ChatGPT, etc.) and how to get extra information about how the AI is thinking.…
-
Writing good docs is important for agentic AI and Model Context Protocol, and developers are terrible at writing good docs
One quick things up-top: this week (tomorrow!), get an overview and demos of the private AI stack and development frameworks we’ve been working on at Tanzu. Register to check it out online, either live or the recording after the event. Spy on the DM with Model Context Protocol Servers in Java Here’s my latest walk-through…
-
Model Context Protocol has prompt injection security problems – There’s a lot of security work TBD with MCP. // “The curse of prompt injection continues to be that we’ve known about the issue for more than two and a half years and we still don’t have convincing mitigations for handling it.”
-
Is Fine-Tuning or Prompt Engineering the Right Approach for AI? – As it says.
-
Extending AI chat with Model Context Protocol (and why it matters) – Adding plugins to the AIs, the hope being that wide community of developers will form, extending the functionality of the AIs. I’ve seen this in practice with Spring AI and Claude and is very promising, and easy.
-
ChatGPT vs. Claude vs. DeepSeek: The Battle to Be My AI Work Assistant – Good overview of what Claude is good for and what ChatGPT is good for.
You must be logged in to post a comment.