Alex Albert Profile picture
Jul 15 2 tweets 1 min read Read on X
Good news for @AnthropicAI devs:

We've doubled the max output token limit for Claude 3.5 Sonnet from 4096 to 8192 in the Anthropic API.

Just add the header "anthropic-beta": "max-tokens-3-5-sonnet-2024-07-15" to your API calls. Image
You can also go test it out right now in the Anthropic Console Image

• • •

Missing some Tweet in this thread? You can try to force a refresh
 

Keep Current with Alex Albert

Alex Albert Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

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

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @alexalbert__

Jul 9
We've put a lot of work into the Anthropic Console the past few weeks and I'm excited to share the latest updates with y'all.

Turns out Claude is pretty good at prompt engineering so we've integrated Claude everywhere: Image
1) Prompt generator

Input a task description and Claude 3.5 Sonnet will turn the task description into a high-quality prompt for you.

Gets rid of the prompting blank page problem all together.
2) Generate test data

Now that you have a prompt, you probably need some test cases to run it against. Claude can generate those test cases.
Read 7 tweets
Jun 25
We just refreshed the claude dot ai UI and added some new features that I think are pretty useful.

Let's dive into them: Image
1) Sidebar

A new sidebar appears when you hover over the far left side of the screen.

You can also now star chats that you come back to often. This has been a huge quality-of-life improvement for me. Image
2) Projects

You can now create custom knowledge bases called Projects with your own files, docs, code, etc. When you start a new chat within a project, Claude has access to all that info.

On the Team plan, you can share and collaborate on these projects with your teammates.
Read 5 tweets
Jun 21
In the lead up to the Claude 3.5 Sonnet launch, we created a Slack channel at Anthropic to share our favorite Claude-generated artifacts.

I scrolled back through and found 7 of my favorite things Claude made:
1) WebGL particle simulators
2) Really good mermaid diagrams Image
Read 8 tweets
Jun 20
Claude is starting to get really good at coding and autonomously fixing pull requests. It's becoming clear that in a year's time, a large percentage of code will be written by LLMs.

Let me show you what I mean:
To start, if you want to see Claude 3.5 Sonnet in action solving a simple pull request, here's a quick demo video we made.

(voiceover by the one and only @sumbhavsethia)
In our internal pull request eval, Claude 3.5 Sonnet passed 64% of our test cases.

To put this in comparison, Claude 3 Opus only passed 38%. Image
Read 7 tweets
May 31
Excited to announce that we’re spinning up an AI educational program and we just released our first course on tool use!

Let me walk you through what it covers: Image
The course is structured in 6 notebooks and is entirely self-driven.

It takes you from knowing nothing about tool use all the way to building a full-scale chatbot that can autonomously use tools. Image
If you've ever struggled to conceptualize how tool use works or you just want to learn how to optimize your tool use prompts, you need to check this out.

You don't even have to read all of it (although you should!) -- personally, I've got a ton of value out of all the diagrams. Image
Read 6 tweets
May 10
We just shipped two new features to our console that I think are going to completely change prompt engineering with Claude.

-Prompt generator: Claude writes your prompts for you.
-Variables: Easily inject external info into your prompt.

Let’s walk through how they work in five steps 🧵
1) When you open up the console dashboard, you will see the "Generate a prompt" button. Image
2) Once you click that, a pop-up will appear. Here you can input a few basic details about your task.

I selected one of the example tasks that prompts Claude to act as an email support agent and clicked “Generate Prompt” Image
Read 6 tweets

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us!

:(