CODE - AI Dynamics

For code? For writing I still find ChatGPT better. Claude’s ‘personality’ can be somewhat sanctimonious – o1 is much more willing to collaborate with me. What y’all use for your needs and what works best?

→ View original post on X — @ninadschick

23 January 2025

Google Announces Parfait: Private Aggregation & Federated Learning

By

@googleai

–

22 January 2025 21h41

Announcing Parfait — private aggregation & retrieval, federated, analytics, inference, & training — a GitHub organization that we’ve developed to demonstrate our state-of-the-art methods across 4 privacy pillars. Learn how it was created & is being used →
https://
goo.gle/4axVNfN

→ View original post on X — @googleai

22 January 2025

Open Source Email Assistant Ranks #9 on Product Hunt

By

@hwchase17

–

22 January 2025 20h16

I launched an email assistant that accidentally became the #9 launch on product hunt a few days ago (just finding out now) Fully open source so check it out here: https://
github.com/langchain-ai/e
xecutive-ai-assistant
… Never check emails again!

→ View original post on X — @hwchase17

22 January 2025

Write LLM Evaluations Like Software Tests

By

@hwchase17

–

22 January 2025 20h02

write LLM evals like you write software tests (pytest/vitest/jest)

writing software tests is standard practice. writing evals for LLMs is equally important, but we don't see it as common place yet

we hope this helps bridge the gap! https://t.co/GZozKNbOw0
— Harrison Chase (@hwchase17) 22 janvier 2025

write LLM evals like you write software tests (pytest/vitest/jest) writing software tests is standard practice. writing evals for LLMs is equally important, but we don't see it as common place yet we hope this helps bridge the gap!

→ View original post on X — @hwchase17

22 January 2025

Build First, Optimize Learning Curve After Implementation

By

@hwchase17

–

22 January 2025 19h52

Step 1 make it work, step 2 lower learning curve Doing step 2 without step 1 is silly

→ View original post on X — @hwchase17

22 January 2025

Upcoming Chapter Content and Bonus Multi-Head Attention Materials

By

@rasbt

–

22 January 2025 18h59

Yes, stay tuned! (And there's also the "Comparing Efficient Multi-Head Attention Implementations" bonus content if you are still bored after completing the chapter :))

→ View original post on X — @rasbt

22 January 2025

Building LLM Agents with Computer Use Capability

By

@andrewyng

–

22 January 2025 18h59

Our first short course with @AnthropicAI! Building Towards Computer Use with Anthropic. This teaches you to build an LLM-based agent that uses a computer interface by generating mouse clicks and keystrokes. Computer Use is an important, emerging capability for LLMs that will let… pic.twitter.com/ghG3uGcRuP
— Andrew Ng (@AndrewYNg) 22 janvier 2025

Our first short course with @AnthropicAI
! Building Towards Computer Use with Anthropic. This teaches you to build an LLM-based agent that uses a computer interface by generating mouse clicks and keystrokes. Computer Use is an important, emerging capability for LLMs that will let

→ View original post on X — @andrewyng

22 January 2025