AI Engineer (@aidotengineer) 's Twitter Profile
AI Engineer

@aidotengineer

A network of software engineers enhanced by and building AI products & infra. Join 2k AI Engineers & Founders at World's Fair '24 in SF, June 25-27. #AIEWF

ID: 1376308155626360837

linkhttps://ai.engineer calendar_today28-03-2021 23:00:28

1,1K Tweet

13,13K Followers

5 Following

AI Engineer (@aidotengineer) 's Twitter Profile Photo

Tinkering with side projects & Claude 3.5 Sonnet this weekend? In this 90-min workshop, Zack Witten (staff prompt eng Anthropic) uses prompts from attendees & takes them to the next level. It's truly a prompt masterclass. Full workshop now available👇 youtube.com/watch?v=hkhDdc…

AI Engineer (@aidotengineer) 's Twitter Profile Photo

According to Factory, an Agentic System is a system that exhibits planning, decision-making, & environmental grounding. Learn about the intricacies of this architecture and how to build it in this talk from their CTO Eno Reyes! Now available 👇 youtube.com/watch?v=bjNYEc…

AI Engineer (@aidotengineer) 's Twitter Profile Photo

Language and culture are now engineering skills. In this popular workshop, Manuel Odendahl provides expert guidance on working with LLMs based on 25 years programming and over 3 years working directly with LLMs. Full workshop available now! youtube.com/watch?v=zwItok…

Sandra Kublik (@itssandrakublik) 's Twitter Profile Photo

Really enjoyed sharing the decisions we've made building the latest Command R and R+ at AI Engineer this year. You can now check out the talk on YouTube p.s. it's very timely! 👀

Latent.Space (@latentspacepod) 's Twitter Profile Photo

🆕 pod: Efficiency is Coming: 3000x Faster, Cheaper, Better AI Inference with Nyla Worker of NVIDIA, Convai, @googleai! The commoditization of intelligence takes on a few dimensions: Time to Open Model Equivalent: 15 months between GPT-4 and Llama 3.1 405B (h/t

🆕 pod: Efficiency is Coming: 3000x Faster, Cheaper, Better AI Inference

with <a href="/nyla_worker/">Nyla Worker</a> of <a href="/nvidia/">NVIDIA</a>, <a href="/convaitech/">Convai</a>, @googleai!

The commoditization of intelligence takes on a few dimensions:

Time to Open Model Equivalent: 15 months between GPT-4 and Llama 3.1 405B (h/t
AI Engineer (@aidotengineer) 's Twitter Profile Photo

Interesting AI/UX case study worth looking into: Hyperspace youtube.com/watch?v=-zzP0E… Among other things, they've built a generative browser that empowers users to steer agentic search via direct edits of the React Flow nodes generated from the Hyperspace DAG orchestration

AI Engineer (@aidotengineer) 's Twitter Profile Photo

Pydantic is all you need was one of the top talks from Summit 2023, with nearly 200k views. But is Pydantic still all you need? In this talk, jason liu argues yes. Learn why in his full talk here! youtube.com/watch?v=pZ4DIH…

jason liu (@jxnlco) 's Twitter Profile Photo

I'm not even arguing, I'm just stating the facts. OpenAI literally agreed that within a year, all the providers' SDKs will be taking Pydantic, and as long as you're using Python, Logfire will be all the ops you need.