The future of AI is agent marketplaces. Ryan Booth's A2A/AP2 demo shows how agents discover, negotiate & transact autonomously. This changes everything about digital commerce 🧵👇 https://t.co/nEhI965PfY

If you are in the Austin area for #SXSW, swing by the Austin LangChain Meetup on Wednesday for a special round of lightning talks and network at the after party. See you there! https://t.co/zmAUIUysHw https://t.co/txHyJ8KFrB

I will be in ATX this week to present on GenAI integrations into developer workflows with the LangChain GitHub toolkit. We have a great lineup this month, so don't miss out. See everyone there!! https://t.co/7hgxXQtci1 #GenAI #AIAgents #LangChain #DevOps #NetworkAutomation

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)

Check out my latest article: Harnessing Collaboration in AI Agent Workflows: Group-Chat vs. Structured Workflows https://t.co/EZYhiHZQX2 via @LinkedIn

1. Real time translation

@TheCMReed @TelemetryNow season 2 episode 1 comes out tomorrow, and the great @that1guy_15 is on

For managers who want to encourage AI use in their teams, psychological safety is a good guide: 1) Share with your team that you will be exploring AI together, no one knows what it can do so you need help 2) Publicly share mistakes you make 3) Demonstrate curiosity & experiment

This was really fun to present at #nanog90 #Golang for network engineers

I've had a lot of people ask if my art is on @instagram, so I finally set up an account. Everything is for sale, and I have lots more not shown. DMs and feedback are always welcome. https://t.co/aGik8rJZKE #art #abstractart

RAG is one of the best (and easiest) ways to specialize an LLM over your own data, but successfully applying RAG in practice involves more than just stitching together pretrained models… What is RAG? At the highest level, RAG is a combination of a pretrained LLM with an

Hey folks... I have an urgent opportunity for someone that has AWX, Azure, Python, and some networking background. You should be US based. It is remote. I'm gathering more details now, but those are the key skills. If interested DM me. If not, please repost. Thanks!

Check out my latest blog post at @kentikinc looking at the role of AI and LLMs in networking - and big thanks to @that1guy_15 for his helpful thoughts and observations of the state of the industry ---->

Scrum is a cancer. I've been writing software for 25 years, and nothing renders a software team useless like Scrum does. Some anecdotes: 1. They tried to convince me that Poker is a planning tool, not a game. 2. If you want to be more efficient, you must add process, not

I got my first LLM (CodeLlama) up in #AWS SageMaker this weekend. Pretty simple to get your whole ML pipeline up and running. Models are a little wonky when you are not pulling them from @huggingface #AutoML looks tempting but I need to wrap an API around this project first.

Llama-2 was almost at GPT-3.5 level except for coding, which was a real bummer. Now Code Llama finally bridges the gap to GPT-3.5! Coding is by far the most important LLM task. It's the cornerstone of strong reasoning engines and powerful AI agents like Voyager. Today is

[NEW EPISODE] Demystifying the role of AI and large language models in networking with @that1guy_15

🪙Tokens are one of the first things people hear about when they come across large language models like ChatGPT. What is a token? a sequence of unicode characters converted into a number. These numbers are then how the text you send to the LLM are represented internally inside

A big issue with building LLM search is that there’s too many options for retrieval and it’s not clear which ones are better than others 🤔 ❓ Top-k has its downsides, but should I do hybrid search? Knowledge graphs? ⚠️ What if one method works better for some questions but worse

In #AI, transformers are king when building models. Here is a great visual breakdown of what the heck a transformer is and how it is built. https://t.co/rkeSUl590S