Building agents with Claude 3.7 Anthropic just released Claude 3.7, a hybrid reasoning model. Here, we share some tips for prompting / usage / configuration of the model. We also show how to build tool-calling agents w/ configurable reasoning. Video: https://
youtu.be/sHcu0YX-1u4
GENERATIVE AI
-
Building Agents with Claude 3.7 Hybrid Reasoning Model
By
–
-
AI Democratization Expands with Voice Interaction Access
By
–
AI is the ultimate democratizer, putting knowledge, inspiration, support, and more at everyone’s fingertips. Today we’re making that more accessible for everyone, whether you’re deep-diving something complex or want to talk vs type. Rolling out now!
-
Microsoft Removes Usage Limits for Copilot Voice and Think Deeper
By
–
Copilot users have spoken! We’ve seen incredible growth for Voice and Think Deeper, and have more and more people telling us they’ve hit those usage limits. Sooo…we’re getting rid of them. https://t.co/tczuRbjVP5 pic.twitter.com/giCyPDAWrL
— Mustafa Suleyman (@mustafasuleyman) 25 février 2025Copilot users have spoken! We’ve seen incredible growth for Voice and Think Deeper, and have more and more people telling us they’ve hit those usage limits. Sooo…we’re getting rid of them. https://
microsoft.com/en-us/microsof
t-copilot/blog/?p=4201&preview=1&_ppp=eee005a8d1
… -
pix2pix: Understanding GANs with Image Input Architectures
By
–
pix2pix was actually a GAN! Just one with an image input. as usual, there are more caveats and exceptions than rules. https://
arxiv.org/abs/1611.07004 the distinction i've always kept in my head was that the "generative models" are such that the model (i.e. the neural net) directly -
Copilot + VSCode ineffective, IDE with agents much better
By
–
Oh yes, we don't have the same experience with the tools or the feedback at all. (Personally, I've never been able to use Copilot + VSCode because it was so crappy, whereas with IDEs with agents it's a whole different story.)
-
Claude 3.7 Sonnet’s Impressive One-Shot Code Generation Abilities
By
–
One of the things we've been most impressed by internally at Anthropic is Claude 3.7 Sonnet's one-shot code generation ability. Here are a few of my favorite examples I've seen on here over the past day:
-
Gemini Flash 2: Best Data Extraction Model at Competitive Pricing
By
–
Gemini Flash 2 is the sleeping giant: it is the best model for data extraction with the best prices. Here's our notes. • Flash 2 Pricing: $0.10 / 1M input tokens, $0.40 / 1M output tokens.
• Supports multimodal inputs: Text, Image, Video, Audio
• Supports PDF inputs
• -
Claude 3.7 Sonnet Performance Limitations in Math Competitions
By
–
"why isn't claude 3.7 sonnet better at esoteric competition math problems"
— Alex Albert (@alexalbert__) 25 février 2025
we found it didn't generalize to becoming a pokemon master https://t.co/tjkKnHprQ5"why isn't claude 3.7 sonnet better at esoteric competition math problems" we found it didn't generalize to becoming a pokemon master
-
Claude’s Improved Reasoning Capabilities Detailed
By
–
And for those curious about Claude's improved reasoning capabilities, we go into even more detail in this thread:
