atonse

Right, and over time the number of HW4+ cars will increase, right?

I can't speak to FSD's quality on HW3, I never had FSD on my Model 3. I did have EAP and it worked really well on highways.

But what is your argument? newer tech will bring improved outcomes? I'm sure HW5 will be even better. But that doesn't change the fact that FSD (on HW4 vehicles of which there are tons), is really good.

This is a really good first step that's citizen facing, what I would love eventually is embracing the whole agentic workflows and actually exposing MCP to tools for gov services - then, say, a law firm's AI could file court documents with MCP tools.

Basically yes, APIs just as good, but that general idea of API-first would eventually also be quite powerful.

It's not new... most people E-file (sure that is a very old service but still an "API" of some form).

So a lot of what this site does is help with the discovery of those disparate sources.

Random people on twitter, sorry, that is the best source I have, not having any visibility inside these companies :)

So I'm happy to accept your view just as easily, stranger on the internet, since it logically makes more sense.

People said Astra was a gut punch and that Anthropic was reeling. (Opus 5 was almost universally panned)

The best thing is that we benefit from these constant back and forth gut punches :)

Also getting to "orbit" is a huge feat, because you need to be going over 17,500 mph (28,000 km/h), get into a designated orbit, and in this case, they're also deploying starlink satellites.

This rocket is the largest rocket ever made by humans, and the largest to even reach orbit, which is insane considering it's by a private company and not a national space program.

Ahhh good point. here are the details I found after reading your reply: https://docs.espressif.com/projects/esp-matter/en/latest/esp...

It sounds like you might not own an EV.

The #1 thing (in my opinion) that makes a difference in how easy it is to own an EV is whether you have a driveway or predictable parking spot overnight. Then you just stop thinking about this sort of stuff, ever.

In fact, since I got an EV (I have a two-car garage), I have forgotten to even check my gas car's fuel levels and have driven it near empty a handful of times, I simply forget to even check.

And as others have said, unless you're driving 250mi a day, a regular commute, you can recharge your car on a wall outlet. It does about 12 miles of range per hour, you can easily get about 100 miles of range every night.

BTW, I was just researching this last week (the christmas display) and ESP32 has a matter compatible chip now... so you an control all this from Apple Home and the other Smart Home platforms.

Absolutely mind blowing. What a fun time to do side projects.

You added "totally" - as others have said, I don't know if anyone will claim a perfect system with no fatalities, enough stats show that it is already much safer than human drivers.

And the true third party validation is that insurance companies are starting to offer lower premiums the more you use FSD. So their risk models are showing enough improvement that they're putting their money where their mouths are.

The idea that Tesla's FSD is not ready for the mainstream is quite outdated, given that tons of Tesla owners are already using it daily, not just your early adopter types.

This is from ten years ago. Tesla's vision only FSD is extremely good now. It has been for at least 18 months or longer.

Mostly custom. Full data model and full web and mobile app to help run day to day operations.

The agent has switched a few times, initially NanoClaw, then Hermes, and now Vercel's Eve (maximum customizability).

NextJS/Shadcn web app, postgres db, eve agent layer, MCP tools (over 100 so every single thing can be done by an agent), SwiftUI mobile app, etc.

Integrations with gmail, gcal, gdrive, quickbooks, using mdx for the wiki displays (so we have rich diagrams, 3d models, etc).

We write about it here: https://kznconsulting.com/work/how-we-run-kaizen

Tesla's already solved this - their vision model does this phenomenally well.

And they've demonstrated adding a sidecar LLM to it as well, mostly for these kinds of "read these 3 street signs, what should i do next?" sort of situations.

Ahhh I built an internal set of agents to run our company (finances, all info in the karpathy-style LLMWiki and a database of clients, contracts, billing, time tracking, all managed by MCPs, etc) and it's also called Kai (company name is Kaizen)

Happy to be in such good company!

Yes this is a big part of what has turned me off Opus 5 completely. The other (more dangerous) one is how often it gets assumptions wrong. These both (along with Astra) caused me to split my time 50/50 now between the two models.

Not a day goes by when I push back on something, to which Opus 5 very unambiguously say "You were right, I was wrong" - this never happened so often with past models, nor with Fable.

We'll have to see how much Opus's ability to communicate has improved. It's already giving me better summaries of where we are in the conversation.

I don't quite understand this sort of thing happening. Wasn't the whole point of the internet to be a self-healing network where we route around severed cables, etc?

Or is it that these ATC networks are their own air-gapped network with less redundancy? That just doesn't add up. Or maybe there was only one line going to the ATC, with no multiple "ISPs" like a datacenter would have?

Yeah but are models good enough to review these files and say “i would work better if you worded it this way?”

I am not averse to learning (I spent hours learning Sketchup many years ago when redesigning my garage).

But the time freed up not learning Fusion360 freed up time to learn about different kinds of fasteners, clasps, how to arrange magnets, etc, so I moved the learning to a different place.

Plus avoiding the "wife is angry cuz this project I over-engineered has gone on for weeks unsolved" factor is always a nice bonus.

Wow, at first, I thought "this is wonderfully silly" but within about 45 seconds of playing with it, I instantly wanted the window seat and thought, wow... I could see what it's like to fly over so many cities from above, just like with a window seat.

Nice idea!

I'm so excited about this sort of stuff. ForgeCAD [1] for me was the first mind-blowing application of this a few months ago, where I'm able to just have claude (or codex) write JS that creates 3D Models that I can then print in my 3D printer.

- Built a ring for my compost bin that can properly hold down the plastic bag. This was originally a multi week project because I was also learning Fusion 360 in small 2 hour chunks over many weekends, then with ForgeCAD I had a good prototype in 60 mins with multiple iterations.

- I also built a cover for my overheating Logitech Circle doorbell, snapped a photo, gave it to claude, and claude found all the dimensions on Logitech's website, and then we iterated with 3-4 prints until we had it just right.

This is a whole new set of workflows that are unleashed with agents, even for hobbyists.

1: https://forgecad.io

you’re right, thanks for clarifying!

I keep getting so many warnings about this though - maybe I'm misreading it? is 27 the LAST version with Rosetta maybe?

I feel pretty good about the 27 series in a way I haven't in the past (I've been running iOS 27 and it's working well), except for one thing, they remove x86 support (no more Rosetta), so just keep that in mind in case that might disrupt anything for you.

I actually think this is what they ended up doing - just regular conversations with tool calling into your various apps, behind a Siri AI API. not HTTP based mcps (for now) but rather local ones.

Yeah that's totally fair. So am I, which is why I'm making sure we're still manually testing the hell out of it before we release it.

But our product now has a way more extensive test suite than it ever did, again, thanks to the agents writing pretty damn good tests.

How do you propose getting "rid" of "Vibe coders" (which I'm assuming you're pooling me into?)

I think probably GPT 5.5, or 5.6 Sol - it was ~ 2 months ago.

Each time I get access to a new model, I do two things on all our active codebases:

- Security review of all the code and vulnerabilities (new models will find new stuff)

- Code review of test suite quality, and idiomatic patterns/code for the language of that codebase.

And in the case of swift and kotlin, it's even more important that an agent helps me with the code quality since I don't know what "idiomatic" swift or kotlin looks like, the way I do with JS, Elixir, C#, Ruby, etc.

Others on our team use Android phones. So when I said that we spent the next few days actually polishing it, that's where others came in, providing feedback when they used it.

I could only sweat the details on liquid glass, etc because I'm a daily iOS user.

I used the emulator - but just like I can use an iOS app for 30 seconds and tell you whether it feels native or not, I can't do the same for Android, since I'm not a daily user of Android phones.

And in the past, I didn't care because when I was manually building the app, I would just do my best with react native. But now that I can actually sweat the details (with the help of agents), I do want to hear from android users and use as many OS-native APIs and features.

I answered elsewhere that I don’t personally use Android phones but we have people on our team that do. Which is why I don’t want to personally claim that it feels native.

But yes we are having real Android users test it.

So it’s quite the contrary. I care MORE what real users say. I can only guarantee that the app does things when I tap. So I’m not trusting the agent on UX, only on functionality. But whether it feels native, I am relying on those users in our team.

Maybe. Android might still be a mess, fair point.