This story should be bigger news on HN not maybe just for the aquihire but for the statement of intent market signal the future has Johnny Ive's vibes both OpenAI and Meta have now poached top people from Apple AVP teams + Meta is increasing focus on the Ray Ban formfactor + neither has a mobile phone hardware ecosystem to fall back on as source of compute so next couple of years progress in VLM, DETR, Splats, etc might be shaped by the new interfaces and I am well psyched up to see where this puck is going !!

Is Tesseract still considered the go to here for OCR I would have thought lot of other options are out there now

Chunking on hierarchy is a good and async built in and a cross encoder mode .... I like this project's Keep It Simple Stupid approach without skipping on functions even a basic graph triple. Using this to fill out a PoC mockup could be worth it vs dummy data and just drawing a cloud.

Given 10min of sunlight the body can naturally produce 15,000UI equivalent so I think gp is likely astroturfing for that brand

You are missing the point where accuracy stays the same

Reveal.js vs Sli.dev seems like a toss up I am sure there are nuanced differences or maybe I am missing something obvious ?

There are some niche changes, but on the surface you can pick either one.

I thought for a sec it was insigths.hn revised and back up again I like that you used the Amazon Strands agent framework $2/month is a nice price point I could also see a flat one time X$ + BYO keys approach I signed in through google to test the few threads I have summd look accurate the commenter standout insights check out. I wonder if the agent could setup HN user login and upvote comment etc. Good work pat those agents on the back !

Interesting to see anync event driven stateless runtimes used here this is becoming a trend for multi/sub agent workflows and using queuing systems in some cases like https://deliveryhero.github.io/asya/ (for kubes) lot of different approaches attempting to deal with fan-in conflict locks who would have thought a swarm of idiot savants would introduce coordination problems lol

We think that using event based agents will eventually become the standard. Currently most AI agent frameworks are essentially a single runtime and use "agents" as nodes in a "workflow". This design pattern is fine for most non-developers to automate tasks locally. However we believe that this pattern doesn't scale well especially for developers. Which is why our agents operate their own runtimes as microservices, and "workflows" are the abstraction layer above agents that allow you to connect and attach agents together to do real work (Workflows to-be-announced soon). We separate "workflows" & agents as different layers in the stack, we think this design pattern is the future of agentic.

Dagger (in Docker) had a idea like this while and Pydantic is using external state savers like Temporal.io there are a lot of directions good luck on yours !!

Pydantic also has a first party integration with DBOS, which doesn't require an external state server.

https://ai.pydantic.dev/durable_execution/dbos/

Terminal Bench 2.0 just dropped and a big success factor they stress is the hand crafted phd level rollout tests they picked aprox 80 out of 120 with the incentive that anyone who contributed 3 would get listed as a paper author this resulted in high quality participation equivalent to foundation labs proprietary agentic RL data but it's FOSS.

AI-RAN is the strategic play here because it's unknown (outside of research lab NDAs ?) what potential real-time physical AI/ML implementation will have on the future of edge processing like organizing the low-layer 6G spectrum contention mechanisms. It's a near certainty that custom AI accelerators are a part of every radio base station in the near future so this is not cash investment but a new product line Joint Venture similar to the Intel story.