and also wrote about it https://s2.dev/blog/distributed-ai-agents

That means, coordination is just done over a log with natural language, which allows us to rewire topology of agents mid-run, fork, merge, spawn breakout rooms or build any research methodology on the fly depending on the question. If something goes wrong / crashes, agents can resume from where they left off. Further, if the log or stream is serverless, agents can connect over the log from any machine anywhere in the world and collaborate on tasks / research.

Comments URL: https://news.ycombinator.com/item?id=47225510

Points: 5

# Comments: 1

Comments URL: https://news.ycombinator.com/item?id=45777562

Points: 3

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=45456202

Points: 3

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=45080231

Points: 2

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=44903855

Points: 1

# Comments: 0

Vercel recently released a "resumable-stream" package (https://github.com/vercel/resumable-stream) to solve this problem using Redis as a backing store.

I felt that we could simplify the approach using s2.dev (I'm an engineer on the team), and created a fork which ended up borrowing the API but otherwise completely rewritten: https://github.com/s2-streamstore/resumable-stream

- S2 streams are cheap, so instead of optimizing to flush only when there is another reader, the stream is always created and written to.

- Unlike the typically ephemeral nature of Redis, tokens are always durable, and there are no memory constraints around number of streams or how much data is on them.

- Relies on S2’s built-in concurrency control. A unique fencing token ensures a single writer, and a sequence number is optimistically supplied to match the one expected to be assigned to the next record, to deduplicate in case of retries.

It integrates nicely with Chat SDK, and you can try this out here: https://ai-chatbot-s2.vercel.app by reloading the page during a larger response!

There are some interesting future possibilities, like building a multiplayer chat experience around shared streams.

Comments URL: https://news.ycombinator.com/item?id=44805545

Points: 5

# Comments: 0

ps, it is running on fly.io so please don't melt the poor baby

Comments URL: https://news.ycombinator.com/item?id=44043658

Points: 3

# Comments: 0

I have been interested in this since I was in college. I was building a capacity counting system for our gym. Our gym used density.io and seemed like a waste of money and I though how about if we could have our own solution homegrown by students. But I couldn't get people on board, but I was able to prototype something.

The thermal camera is just a pixel array, which each pixel is denoting its temperature. Kitchens are tricky, since hot items can gravely affect the temperature readings. I use it at the entrance to check if my roomie is in or not/.

you have drivers for amg8833 in rust and c I believe, but adafruit stuff is good in python so I would say its a good place to start IOT projects! You can write your own drivers, which is quite fun!