Matt

@mane

573 Following

2995 Followers

dawufi pfp

vibe check is back for season 2! kicking off with the one and only legendary devrel for /eigenlayer @mane ! experimenting with expanding the surface area that we check vibes on, we cover: - what eigen layer is - pvp vs p2p - and of course memecoins Really fun episode - thanks so much to @mane for coming on, and as always shout outs to @pods for the publishing platform lastly - friendly reminder that i'm on two podcasts now :) make sure to follow rubicon on twitter to keep up with @eulerlagrange.eth and myself exploring disruptive ideas in the crypto world: https://x.com/Rubicon_pod https://pods.media/vibe-check/vibe-check-14-matt-murray wuf out!

0 reply

3 recasts

11 reactions

avi pfp

recorded our first podcast of the year! @mane and i talk about @anoncast, @33bits and anonymous forums in general we discuss the backstory of $ANON, current state of client side ZK proving, the meaning behind the name "33bits" and more https://www.youtube.com/watch?v=kbMmii4rLDk&t=20s

1 reply

3 recasts

12 reactions

Matt pfp

Interested in this, what would the group discussions entail?

1 reply

0 recast

0 reaction

Matt pfp

Building effective agents - Anthropic

0 reply

0 recast

1 reaction

Matt pfp

Article - https://www.anthropic.com/research/building-effective-agents

0 reply

0 recast

1 reaction

Matt pfp

Parallelization Sectioning: Breaking a task into independent subtasks run in parallel. Voting: Running the same task multiple times to get diverse outputs. Orchestrator-workers A central LLM dynamically breaks down tasks, delegates them to worker LLMs, and synthesizes their results Evaluator-optimizer One LLM call generates a response while another provides evaluation and feedback in a loop

1 reply

0 recast

1 reaction

Matt pfp

Anthropic released a great breakdown of common agent design patterns Feels like a great reference for a lay of the land and the variety of approaches you could take. Really good diagrams to illustrate these flows Starting Point - The Augmented LLM Agents are essentially LLMs enhanced with retrieval, tools and memory Design Patterns: Prompt Chaining Prompt chaining decomposes a task into a sequence of steps, where each LLM call processes the output of the previous one Routing Routing classifies an input and directs it to a specialized followup task

2 replies

1 recast

9 reactions

Matt pfp

What's the timeframe where we shift from recommendation systems to more proactive agent information flows? ex: ingesting news & social feeds --> creating a personalized daily newsletter or navigable source

0 reply

0 recast

5 reactions

Matt pfp

For it, turns out it was one of my most listened to songs last year

1 reply

0 recast

1 reaction

Matt pfp

locking in https://www.youtube.com/watch?v=vBCNlxFTkJk

4 replies

11 recasts

94 reactions

Matt pfp

some confuse P2P and PVP

1 reply

0 recast

4 reactions

Matt pfp

Might get back on Farcaster, it’s been quite a minute. Spending my time on Twitter but finding balance

1 reply

1 recast

10 reactions

Matt pfp

0 reply

0 recast

4 reactions

Matt pfp

Check out FlappyCaster mini app! I just scored 21 points! https://flappycaster.com/api/frame/share/score?score=0&usersPlayedCount=10638&t=1732345963426

0 reply

1 recast

4 reactions

Matt pfp

0 reply

0 recast

2 reactions

Matt pfp

Happy to provide feedback!

1 reply

0 recast

1 reaction

Nader Dabit pfp

If you're coming to DevCon and looking for something healthy, positive, and fun to do that isn't a conference or a party / rave. 🇹🇭 We’re cohosting this run club on November 14! Join me @abruzuc @jarrodwatts @mane + others. https://lu.ma/grucwndy

6 replies

31 recasts

71 reactions

Matt pfp

0 reply

0 recast

6 reactions

Matt pfp

1 reply

0 recast

1 reaction

Matt pfp

0 reply

0 recast

0 reaction