NEW - Anthropic Updated Claude Models & Computer Use Agents!!

In this video, I look at the latest versions of Claude models that have just dropped today and also how they're introducing their new computer use feature which will allow us to be able to basically have agents interact with our computers.

For more tutorials on using LLMs and building agents, check out my Patreon

🕵️ Interested in building LLM Agents? Fill out the form below

👨‍💻Github:

[RichardWatson]

Should be some online VM desktop you could use the computer use on. Reduce risks and give more people a way to use it safely.

[richardadonnell]

🎯 Key points for quick navigation:

00:00:00 *🚀 Introduction and New Model Overview*
- Announcement of two new Claude models: 3.5 Sonnet and 3.5 Haiku.
- Overview of how the new models fit into existing frameworks.
- Mention of Opus 3.5, which is anticipated but not yet available.
00:01:00 *📊 Performance and Benchmark Comparisons*
- 3.5 Sonnet outperforms previous models on most benchmarks.
- Benchmarked against GPT-4o, Gemini 1.5 Pro, and others.
- Highlight of SWE Bench score improvement from 33.4% to 49%.
- Focus on agentic tool use and coding enhancements.
00:03:27 *⚡ Haiku Model Details and Future Potential*
- Haiku 3.5 expected to outperform Claude 3 Opus.
- Limitations: initially released as text-only, with image input support to follow.
- Potential for fast and affordable performance in many tasks.
00:04:23 *🖥️ API Development and Computer Interaction*
- Introduction of an API that enables Claude models to interact directly with computers.
- Allows searches and task execution through a browser autonomously.
- Benchmarked on OSWorld; possible risks highlighted.
00:06:20 *🧪 Demonstrations and Precautions*
- Demo videos showcase model abilities like filling Google Sheets and performing searches.
- Identified risks include errors during testing and potential misuse.
- Suggested using a separate computer for safety when testing the API.
00:08:25 *📋 Conclusion and Summary*
- Summary of the benefits of using Sonnet for coding and Haiku for fast tasks.
- Speculation about the release of Opus 3.5.
- Invitation for viewer feedback and future exploration of the API usage.

Made with HARPA AI

[drhxa]

Used new Sonnet 3.5 today for work (coding). It's def a solid improvement. I'd say it's on par with o1-preview or o1-mini but much faster.

Haven't had a chance yet to try it with very long instructions because claude models are typically super strong on instruction following. Can't wait to keep building with it tomorrow!

[jeffsteyn]

Computer use is going to be a game changer

[devanshoo]

computer use has a big big usecase for Software QA specifically. Really excited

[billybofh]

A very small thing - but one of my 'bots' that was using sonnet 3.5 seems to now be automatically aware of the tool/function-calls it has available. As in, it'll mention them in it's response as 'something you might want to ask me to do'. Not sure if it's just a quirk - but I never had previous models seem user-facing 'aware' of their available tools. It's responses with an eye to a nuanced take on it's system prompt also seems much better. Looking forward to trying Haiku!

[wendten]

Why did they not change the name to Claude 4 or at the very least 3.6.. Isn't that what those numbers are for?

[ukoni]

Thats why he was saying AGI by 2026..the new era of autonomous machines

[aliyananwar]

computer use is beyond over hyped agents of langchain, we need powerful ocr and and powerful llm for this to replicate

[alchemication]

Looking forward to compare gpt4o-mini and the new haiku, as they definitely have their place. And trying the new sonnet asap obviously (assuming price is same..)

[pure]

The next question is how to make all agents work together and check/verify in one company? Maybe beyond one company.

[marilynlucas]

I've been waiting for a model that can use blender efficiently. i describe the scene i want and then it gets to work to build the scene in blender

[sheikhfaizan]

How to use previous model because i wana to use previous model but don't show any option to use previous model

[denijane]

Funny, about 4 hours ago, I got one very unfortunate session with Claude in which it basically forgot Latex. I wonder if it has something to do with the update. Because it looked VERY odd. (like writing pi as a symbol and not as \pi etc).

[-un]

can you make a video on how to use the computer model to do an action 🙂

[mybocks]

LMAO! 😂 Yellowstone is quite beautiful ❤️

Computer use will be great ONCE IT IS RUN LOCALLY. I don't trust cloud machines owned by others to be using my computer, that makes it not my computer anymore and it's a pain making a VM for each time.

[AdamTwardoch]

Version numbers are kind of useless if vendors don't increase them when they actually upgrade the functionality. I don't know why they wouldn't call the new model Claude 3.6 or so.

[hqcart]

It's playwright framework or similar, then LLM interacts with it, it's not new.

[dankprole]

Software services should provide APIs and SDKs. The idea of an agent clicking around a screen like a person is so unbelievably dumb and inefficient.