I couldn't build this even with Claude Mythos, I have no freaking clue what this stuff is, and I'm a full time software developer that understands performance optimization and even has used SketchUp a lot.
I'm telling you, I simply couldn't do it. Unless the prompt is "copy every single feature in AutoDesk Fusion 360" and sit back, and even then, I wouldn't even know where to start with testing it, knowing whether it works properly, and whether the various tools are useful, performant, etc.
Let's not assume that the code is the most important part, it's important, but domain knowledge is still very important.
In fact, my pet peeve is why can't 1Password build in the ability to "remotely" approve something via the 1Password app? I'd get a push message, hit allow, and it does the negotiation in an e2e encrypted way.
Then I could approve something my agent needs when I'm not at the computer. Service Accounts are a crappy solution to be honest.
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.
I don't know why anyone was saying that when Anthropic clearly knew Opus 5.5 significantly outperformed Astra at the time of Astra's launch. I think it might be a good exercise to go back and find out who called Astra a "gut punch" and lower your credence in their future claims.
I actually heard the opposite, the folks at Anthropic felt pretty confident they were ahead after the Astra release because it wasn't as good as they were expecting.
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.
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.
> It does about 12 miles of range per hour, you can easily get about 100 miles of range every night.
I wonder if the residential 230v standard in many parts of the world contributes to EV adoption. A standard household outlet can do up to 3.5kw on 230v whereas in North America a standard outlet is 15A at 120v which only gives you a max of 1.8kw (realistically more like 1.6kw). To get increased power you need a 240v circuit which is typically only for selected appliances like dryers, induction cooktops, heat pumps, etc.
>I wonder if the residential 230v standard in many parts of the world contributes to EV adoption.
The veracity to which the government enforces rules that make work for variorus electrical professionals and manufactures has a lot more to do with it IMO.
In some places an EV charger install is a "here's the best we could do, you might trip the main breaker if you fast charge while running the stove and water heater and dryer all at once"
In some places it's permits and panel upgrades, and, "have to bring X up to code while we're at it, that'll be <1/3 cost of car>", and, and, and, (to the cheers of the same demographics who complain adoption is to slow no less).
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.
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.
From that same article - "The agency said it has identified nine crashes potentially linked to the issue, including one fatality and two involving injuries. It is also reviewing six additional crashes that may be related."
Fifteen crashes - though not to be trivialized - is not a damning number at all in this context. What's more, per the article it's unconfirmed that the crashes are related, so it's hardly fitting to dismiss Tesla's approach based on this.
I think it's great that serious efforts are being made in different approaches to autonomous driving - and in this thread's context, it seems possible that Tesla's approach might eventually be revealed as the optimal approach given modern AI.
Only for 2024 or maybe late 2023 cars and later (HW4). The older the car is the worse the FSD software is because the old hardware can't run the latest software.
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.
Anecdotes. Only accident rate per mile driven (compared to human drivers' rate) is a relevant comparison. I don't think that any self-driving system will ever be absolutely perfect (all such complex non-linear systems are to some degree probabilistic and chaotic), but as long as the accident rate is lower than the human accident rate, I would consider it solved.
It's Lego mindstorm logic level to drive a car on the motorway, so per mile is an absolutely insanely bad metric in general.
Per mile inside cities or other difficult scenarios are what may get close to an actually meaningful metric. That's why Tesla is very misleading and waymo is much more legit.
Cute, but no. Can't compare a self-driving system that's only willing to work in a subset of conditions humans drive in, to humans driving in all those conditions.
> Only accident rate per mile driven (compared to human drivers' rate) is a relevant comparison
This is such an insane take I see all the time from self-driving boosters
If a self driving car glitches out and crashes in some edge case pathological scenario we don't just accept that as totally fine because its hidden under big statistics
The reason why a crash happened does matter, its not just about aggregate statistics
As a thought experiment if I have a perfect self driving system but I add some code that purposefully crashes 1 in 10 million rides are you ok riding in it since the aggregate statistics look good?
> As a thought experiment if I have a perfect self driving system but I add some code that purposefully crashes 1 in 10 million rides are you ok riding in it since the aggregate statistics look good?
Do I know about the purposefully added harmful code? If yes, I would demand you remove it, because why not. If I don't know about the code, I would be OK with it, since it's clearly still more safe than the alternative and apparently cannot be made even better.
You seem to be neglecting the important part of that scenario where you're other option you have to compare it to is a human driver that will randomly get it a crash at some higher rate.
You're making it sound like the obvious answer is the irrational one.
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.
Note that the article has no info on whether it's FSD or Autopilot and whether they contributed to the fatal crashes. "Verified engaged" means ADAS was active at some point in the interval from T-30s to the end of the accident. The total number of collisions is not normalized by the miles driven.
It also has no info on what hardware+software version was in use. The older cars are significantly less capable but there are far more of them on the road.
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)
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'm telling you, I simply couldn't do it. Unless the prompt is "copy every single feature in AutoDesk Fusion 360" and sit back, and even then, I wouldn't even know where to start with testing it, knowing whether it works properly, and whether the various tools are useful, performant, etc.
Let's not assume that the code is the most important part, it's important, but domain knowledge is still very important.
reply