Post

This Thread may be Removed Anytime!

Twitter may remove this content at anytime! Save it as PDF for later use!

More from @skirano

Pietro Schirano

@skirano

Dec 21, 2024

If you're a CS student worried about recent AI developments, read this.

First, intelligence is not a measure of effectiveness. I've managed many people throughout my career, and if you don't know how to employ their intelligence effectively, raw ability simply doesn't matter.

This is where AI tools are right now, and I expect them to stay this way for a while. While reaching incredible levels of intelligence, we still don't know how to direct them most effectively. Your job WILL change - that's a fact. But it won't be a straight replacement as some claim.
It will be an evolution. Your ideas and design/product decisions will become even more valuable.

Read 8 tweets

Pietro Schirano

@skirano

Dec 12, 2024

Introducing Claude Engineer V3 🚀

The first self-improving assistant capable of not just running tools, but creating them on the fly whenever needed!

Want a web scraping tool? Just ask Claude, and it will build one for you.

This is my most ambitious release yet. I started exploring self-improving frameworks a few months ago, and after lots of usage and testing, it does feels like the future of computing.
github.com/Doriandarko/cl…

Claude becomes an extension of my thoughts. When I ask it to do something beyond its capabilities, it doesn’t stop—it builds the tools needed to get the job done.

Read 9 tweets

Pietro Schirano

@skirano

Nov 25, 2024

Today @Anthropic is releasing MCP, a framework that allows Claude to run servers, giving it superpowers and effectively turning the Claude app into an API.

We created some server that I think you'll love!

FileSystem: Claude can create, read, and edit files and folders locally.

Brave search: Claude can search the web for anything, and provides enrichments for location search results. leveraging Brave web search and local search api.

Servers can even be combined, like in this example where I am first asking to do a deep web search about Pietro Schirano, then, create an entire website about the findings using Tailwind in a single index file at a specific local path.

Read 4 tweets

Pietro Schirano

@skirano

Sep 30, 2024

o1-engineer is here! 🚀
A coding assistant built from the ground up to leverage o1 reasoning capabilities.

It can create and edit multiple files or entire folders,
plan complex projects, execute them, and write code reviews.

All from your terminal 👨‍💻

💬 You can chat regularly or execute commands:
/create to create files or folders
/edit to edit file, files, or folder content
/add to add files or folders to the chat context
/planning to create detailed plans
/review to create code reviews that you can use directly

Repo here. Star the repo so you can keep track of updates and improvements. ⭐️
github.com/Doriandarko/o1…

Read 6 tweets

Pietro Schirano

@skirano

Sep 15, 2024

Here are some o1 prompt techniques I’ve discovered that have worked well for me so far and can likely be applied to any reasoning LLMs.

1. Be explicit about the reasoning chain
By requesting a detailed breakdown, you encourage the model to organize thoughts methodically.

2. Guide decision-making with hypothetical scenarios
Providing specific criteria guides the model through a structured analysis, yielding a more nuanced response.

3. Facilitate multi-step problem solving (especially for coding)
Breaking down the problem encourages the model to think through each step, reducing errors and enhancing clarity.

Read 6 tweets

Pietro Schirano

@skirano

Sep 3, 2024

https://twitter.com/alexalbert__/status/1831022348784542090

I'm excited to share that I've been partnering with the @AnthropicAI team to build a beautiful, fully customizable customer support AI agent with RAG.

Using Claude, NextJS, ShadcnUI, and AWS Knowledge Bases.

The entire repo is available on GitHub via the Anthropic Cookbook. ✨

https://twitter.com/alexalbert__/status/1831022348784542090

It's a great starter app for anyone to really take advantage of Claude's capabilities.

You can see Claude thinking in real-time, as well as the mood of the user interacting, if any documentation has been used, and even the category to which the customer problem is connected.