Steve & GN more broadly are like the YouTube channel equivalent of the guy that always brings receipts and applies a level of pedantisim to the word choices used that you'd usually only find in the legal profession.
I used to just use them as a detailed reference for hardware performing metrics, but they honestly put large media outlets to shame with the comprehensiveness and depth of their reporting.
Steve is like the pointy tip of the spear for the Fourth Estate. He has abbsolutely no qualms about burning bridges with subjects when he smells blood, unlike a lot of the reporting you see from the Times, WSJ, and the Post.
Bloomberg is the only outlet that seems to hit C-Suite execs as hard, but they're uniquely empowered by financial markets to do that and still seem to pull their punches with politicians.
I had a similar thought too looking at that photo and then I realized that personally, the only computer I've ever used out 'in the field' for extended durations was a MBP when I was working on an autonomous drone project senior year of undergrad.
It was November/December in Iowa, so it was freezing and the local R/C club airfield was nestled between an ocean of corn fields and the city dump, so it smelled terrible.
But that 16" MBP was red hot from Android Studio and kept my fingers from freezing, so credit where credit is due. Really fun project too!
It's an OpenAI Dot/Open Claw competitor. Doesn't really seem to differentiate itself meaningfully at first glance.
If I want a persistent agent, I'm still not sure why I'd pick one where I'm locked into a specific model family. Having it "just work" is nice! But this feels like a product area where not being locked into one garden is more important and the net gains are greater.
I like Muse, and OpenAI's Dot. But what will differentiate this for me is the model. I grew frustrated with Muse's lackluster model, and increasingly with OpenAI's Dot as even if it implements my asks with Astra I just have not been to happy with the output. If Claude/Opus can do better, that's all the differentiation I need.
Competition on what to do with it, not on pricing: Dot is free (assuming you've a subscription), Duet isn't. I'd not want precious tokens to be wasted by some random polling Duet may be doing, all while using Opus as its underlying agent.
the trick imo is Opus 5.5 is the only differentiator you need. remember that ClawdBot dba OpenClaw began as a way to harness some ancient Claude model (4.5? lolll) in an always on Telegrammable agent.
It's really a bummer that Dart gets a bad rap, because of its early versions. The recent versions of Dart are a lovely language to work with. Pub is the only package manager I've used that approaches Cargo in quality.
All TypeScript competitors got out-engineered by Microsoft. It’s a triumph of experience over new ideas.
How well designed the initial versions of TypeScript were can be seen by how smoothly later versions were able to build on them, and even after so many major improvements the language has barely a wart (enums probably being the only one).
namespaces are the other one, and that's a fun legacy because Typescript had to implement a half dozen module systems in the early days: no modules (jQuery-era globalThis pollution), AMD, UMD, CommonJS, SystemJS, Typescript's own which was proto-ESM inspired but not ESM, then Typescript's realignment with ESM.
Something of its own sign of Microsoft out-engineering some of the hiccups of the ecosystem as a whole. (I started using Typescript < 1 simply because it was the safest and easiest way to write AMD modules also with an eye to UMD or SystemJS output with just a compiler flag change if you needed to ship something compatible outside the house.)
I'd be interested in using this with something like the new HuggingFace robots. Do you have demos showing how to go from HFlow dataset to training to deploy?
Creating a basic ergonomic example of the full train/deploy loop, using your data engine, for a popular platform in the zeitgeist, will give you a traction boost.
You don't have to innovate on the parts outside your core competency. Have your favorite LLM ingest the Reachy docs, give it control of a robot, and put a lightweight example together. Iterate till you like the example flow and you've purged docs and output text of AI slop, then release!
The requests packages fundamental API is good enough and is now maintained by the PSF. I don't understand why OpenAI and Anthropic don't just throw some $$$ to the PSF for focused improvements and expansion of it.
The maintainers of requests have made it pretty clear that they consider that package feature complete, and have not showed interest in adding native async support to the core.
I have 5 Gbps symmetric fiber in NYC with a Google Fi data only sim as a built-in failover to 5G on my router. It did require some specialized hardware, but it's truly a wonder coming from a kid that experienced dial up.
It really changes the calculus on some things with large volumes of data on my desktop. Admittedly, my desktop maxes out at 2.5 Gbps, but everything else in the house keeps happily chugging along.
I'm shocked Teams + GitHub haven't already done something like this. But I suppose that's asking a lot from Teams.
I've been using Claude and other agents in Slack for some code tasks. It's mostly fine for simpler projects and products. Things like docs or specific libraries. But I'm not really convinced this is the ideal interface yet. Reviews are my bottleneck and GitHub has a great UI for this. Plus, token consumption with Slack is out of control.
Maybe in time this will be the way we work, but for now I still find myself using GitHub, a terminal, and slack together.
I used to just use them as a detailed reference for hardware performing metrics, but they honestly put large media outlets to shame with the comprehensiveness and depth of their reporting.
Steve is like the pointy tip of the spear for the Fourth Estate. He has abbsolutely no qualms about burning bridges with subjects when he smells blood, unlike a lot of the reporting you see from the Times, WSJ, and the Post.
Bloomberg is the only outlet that seems to hit C-Suite execs as hard, but they're uniquely empowered by financial markets to do that and still seem to pull their punches with politicians.
reply