James Sha @_jamessha

Building AI agent simulations @labyrinth_hq_ linkedin.com/in/jamessha/ San Francisco Joined February 2014

Tweets

22
Followers

83
Following

51
Likes

20

James Sha @_jamessha

6 months ago

Made aimlabs gridshot with Claude 3.7 with one prompt, crazy how easy it is to make custom aim training now #Claude37 #VALORANT

0 0 0 95 0

Download Video

James Sha @_jamessha

8 months ago

It was annoying to keep calling our voice agent to test it, so we had automated it. Now we've turned it into a demo - you can have one of our 15 preset "customers" call your agent, or define your own

Neil Garde @neil_garde

8 months ago

It was annoying to keep calling our voice agent to test it, so we had automated it. Now we've turned it into a demo - you can have one of our 15 preset "customers" call your agent, or define your own

0 1 1 257 0

0 0 2 101 0

Neil Garde @neil_garde

8 months ago

Demo here: labyrinth.io/agent-demo

0 1 1 257 0

Try out a demo of our adversarial voice agents! At Labyrinth, we're building a voice agent testing and simulation platform that lets you run your agent against other agents that simulate your customers. Agents can be configured to generate randomized scenarios for your use case,…

1 1 8 288 0

James Sha @_jamessha

10 months ago

Once AI agents start performing human tasks from start to finish, who takes responsibility for errors? Society is set up for individuals to take responsibility for mistakes but individuals rarely work at the same scale as AI.

0 0 0 42 0

Neil Garde @neil_garde

10 months ago

People building voice agents: how do you test out your product? Do you build your own tools just to talk to it?

1 2 2 215 0

Neil Garde @neil_garde

10 months ago

AI Voice agents will be some of most powerful applications of LLMs, but it's been clear there are some challenges in development. Here are the problems we see, and how we're solving them at @Labyrinth_HQ_ 🧵

2 2 5 416 0

James Sha @_jamessha

11 months ago

AI safety is incredibly complex and we all want to prevent the worst outcomes. As it gets easier to create AI companions, we can do more to test and catch problems before they make it to the wild.

Neil Garde @neil_garde

11 months ago

AI safety is incredibly complex and we all want to prevent the worst outcomes. As it gets easier to create AI companions, we can do more to test and catch problems before they make it to the wild.

1 1 14 4K 3

Download Image

0 0 1 177 0

Neil Garde @neil_garde

11 months ago

The evaluation agent lets you prime the opposing agent with a prompt, letting it act out specific scenarios. When you're manually testing your agent, creativity is a big problem, so this lets the agent do the work instead of you.

1 1 0 45 0

Download Image

Neil Garde @neil_garde

11 months ago

How do you manually test your voice agents? We are building a voice agent playground that lets you interact with your voice agent manually, or by simulating a conversation with an evaluation agent.

1 1 0 52 0

Download Image

Neil Garde @neil_garde

11 months ago

🧵 1/ AI evaluation is usually centered on a single output from a large language model (LLM). Did the model generate a good response? ✅ But what if the AI is fully automated, engaging in ongoing, real-time conversations with humans? The problem changes entirely.

1 2 5 431 1

James Sha @_jamessha

3 years ago

Full video: youtu.be/akqcQezTZPA When we started Onyx, Asaf made it his special mission to take a video of me whenever I had a bad hair day. This is the fruit of that labor. Huge thanks to everyone who made Onyx happen! It was a heck of a ride 🙂

0 0 3 0 0

DK @dksf

6 years ago

I've been playing with the @getonyxfit tool for a while and it's been really fun. Amazing that the little device in our pockets has enough sensor horsepower to deliver this unique tracking experience. Check out the video for an impressive demo! 👇

2 2 16 0 5

Pieter Abbeel @pabbeel

6 years ago

SO EXCITED to share that @getonyxfit has publicly launched! 🎉 Everyone who has spent time in my lab, knows how much importance I put on exercise, and not just for myself :) Check it out! Congrats to @asafagus @_jamessha!! Honored to be small contributor to the Onyx team :)