mdeeks

If you aren't familiar with how EBS works and how volumes are warmed, then yes, this is an interesting blog post. Not everyone is an expert. They become experts by reading things like this and learning.

If you didn't know about this EBS behavior it would be logical to assume that booting from scratch is roughly equivalent to starting/stopping/starting again.

Because it is a legitimately useful feature? I've already used it multiple times just today.

It isn't much different than the Github Copilot CLI feature `gh copilot suggest "how do I do X?"`. It actually has a better user experience IMHO. You get to see and edit the suggestion quickly and easily. It's always just a cmd+y away too.

I agree about the trend to stuff AI in everything. This one feels legitimately useful though? One hot key away from asking how to write a command in plain english is kinda nice.

Honestly iTerm has always been loaded with features that of dubious usefulness. They all tend to be useful to someone though. This is just another one on the list.

I think the biggest failure here was the way it was communicated. Extremely ambiguous about WHAT it actually does and any privacy concerns.

> And not for nothing it’s a weird coupling. I can’t think of a single reason I’d integrate with an ai agent in this way over a more unixy approach.

The AI Agent part is a bit weird, but the "Engage AI" feature is pretty nice. Just hit "cmd+y" and type something you want to do like "Clone without blobs", or "get the last two fields from a CSV", and it shows you the command which you can then run with "shift+enter"

If it does do that then yeah, there should be backlash. But I don't see that stated anywhere in the notes nor do I see a hint of that in the app.

The only two AI interfaces I see are the "Engage Artificial Intelligence" menu item where you ask it how to form a command, and then a second interface in the Toolbelt called Codecierge where it tries to complete a task you tell it to do.

Both of which are completely optional and require an OpenAI key. If you do use them you're sending your request to OpenAI but as far as I can tell it doesn't get any of your command history or anything like that.

She posted about it on Twitter: https://x.com/anniealtman108/status/1635704398939832321

There may be other posts, but this is the one that was most widely shared AFAIK

I'm really confused what is going on here with people being so upset. It doesn't do anything unless you provide an OpenAI key. Nothing is sent anywhere unless you actually run the "Engage Artificial Intelligence" command. It's roughly the same thing as asking ChatGPT, but its right in your terminal app.

It isn't always on or anything. It's actually kind of hard to find and use.

Is there maybe something I'm missing? Or is this a general backlash against AI?

I never understood why Hertz did this. I'm a huge fan of our own Teslas (yes, we bought a second one), but when we go on trips I never want to rent one. I had the option and considered it for a second, but I just want my vacation to be as close to zero issues as possible. We don't necessarily know where we will end up driving and I don't want to have to worry about finding a charging station. There is slim chance my hotel has a charger, and when they do, they only have a few.

At home it makes tons of sense to have a Tesla. I have a charger in my garage and I know my regular commute and where super chargers are.

It just doesn't make sense to me to rent an EV right now. Not until chargers are ubiquitous. Maybe for short business trips where you know you'll be in an area that has lots of chargers?

I am aghast at what I just saw. This isn't just "inspired by Linear". It quite literally is a carbon copy of it. I'm unsure how you are able to put this out into the world with a straight face.

When adopting tools into a company there are many factors considered beyond just the product itself. One of the big ones is trust. I can't imagine many decision makers seeing what you've done and coming to the conclusion that you're a business they can trust to weld to their own. Internally we treat most of them as partnerships, not transactional.

People tend to assume tools are easily swappable in organizations. They are not. It is a major risky decision that has large cost, privacy, and security concerns. Attorneys are heavily involved in the process (ask me how I know).

Now we could make this risky and costly bet on a well established, trustworthy company, run by industry leaders... or we could go with a company who is now well known for completely ripped off the design of the former and slapped some AI into it. Which would you choose?

If you want to build a successful company that tries to take down Jira (PLEASE DO), you can't start like this.

Worth mentioning: I don't believe they have confirmed it was FSD yet. It just says Autopilot which can be the basic one which just keeps you in a lane.

In any case it's frightening that any version of it it wasn't capable of detecting a motorcycle in front of the car and stopping.

I just got a FSD trial of 12.3.4 on my Model Y. It's better than I expected, but still feels far from something that can fully autonomously drive. Freeway driving works really well and has for years. Street driving is hit and miss. So much that I basically turn it off unless I'm driving a known good path. It handles intersections, street lights, and stop signs just fine. It goes around cars blocking the road, waiting first for a clear path in oncoming traffic.

On the bad side, it brakes REALLY hard a lot and accelerates REALLY hard off of stop signs.

It often freaks out when pedestrians are near the side of the road. My car came to a rapid full stop because some bikers were standing looking at their phones about 6 feet from a crosswalk. Besides being jarring and annoying, it pissed off and scared the person behind me. The car wouldn't have moved if I didn't disengage FSD.

It drove right towards a very low curb that suddenly appears in the roadway by my house. It's an old curb that sits maybe only 3 inches high but would definitely feel like a slam and maybe damage the tire if we hit it. I'm guessing it doesn't look enough like a normal curb to FSD

There are a bunch of small experiences just like these. I disengage nearly every trip and often at least twice.

Which specific GPT-4 model is this? gpt-4-0613? gpt-4-0125-preview?

I'm assuming it is because Bun uses Discord? There are Discord links on their site and on Github, though the links don't seem to work.

I wonder how much these things weigh. Sadly the first thing that my mind wondered is if someone could attach it to the bottom of a drone. Like the ones the Ukranians are using to hit Russian oil refineries. A lot of those are being shot down by regular soldiers with rifles looking up into the sky.

My guess is the invisibility effect only works at very specific distances and it weighs far too much.

Civ 6 can be entirely played via mouse

I don't think the point for him was to simply find a way to control his mouse. He said at the end of the clip he specifically wanted to help out with Neuralink. He also said the surgery was easy and he was released a day later.

He appears to just think about where the mouse should go and then be able to click and click-and-hold. Seems like multiple inputs which an eye tracker wouldn't do. Unless maybe its just configured to click when the cursor pauses on a spot?

Also the user experience seems better than attaching electrodes to your head. It seems to just work wirelessly. It is always there and sometimes he has to recharge it.

FSD being good isn't really the same as the Robotaxi idea. Robotaxi was where you could rent out your car and it could completely autonomously drive other people for a fare. Your car would make money.

I haven't seen 12.3 but other versions had some frightening mistakes in videos. It feels like it will eternally be 90% there but never actually reach the end goal of completely autonomy.

Personally I love Autopilot even if I only use it to drive on the freeways for me when I'm tired.

A single event isn't a "track record". Though I guess he's been touting the Robotaxi idea for a long time and it still isn't anywhere on the horizon.

I love that one of the first things he said he did was binge on Civilization 6 until 6am. Welcome back, buddy!

Strangely that simple example was the most powerful part for me. I've done that so many times and it was such a fun experience. Now he gets to re-live that joy (and follow up shame) again!

Likely this one: https://caddyserver.com/download

Discouraging? Huge understatement. An auth plugin that refuses to fix multiple high severity vulnerabilities is wild. No one should use this plugin for anything. If I were the Caddy authors I would remove all references to this project and ask that they stop use of the Caddy name.

I have 388 items in my password manager. 138 of them use my email address which was found in this breach :(

Not that you're wrong, but there is no reasonable way to rotate all of those. I guess I'll have to spend a few hours manually going through the ones I care about and rotating them?

There is no such thing as "lift and shift". It is something Azure account reps like to say to make it sound like moving is easy. It sounds like you're picking up some boxes from one side of the room and moving them to the other. When in reality you're rewriting your infra code mostly from scratch.

When we were acquired by MSFT we had the same project. We had to move from AWS to Azure. I made them all stop saying "lift and shift" because in reality it is "throw away all of your provisioning code and rewrite it using Azure primitives which don't work the same way as AWS ones".

It is more akin to writing an iOS app to work on Android.

Looks interesting! We're in the middle of building something similar right now for ourselves. We may look at this as an alternative for ourselves.

By the way, I saw this after a quick glance poking through the code. This isn't encryption, it is hashing. Not sure where or how it is used but it is worth a rename at least: https://github.com/bricks-cloud/BricksLLM/blob/main/internal...

The Flexport CEO said it was an LNG (Liquefied Natural Gas) carrier. https://x.com/typesfast/status/1724150162531201571?s=20

  Keep an eye on whats going on at the Panama Canal. An LNG carrier just paid $4 million to jump the line. This will likely be more common for LNG carriers as their cargo will literally boil off sitting in the hot tropical sun, but it will be interesting to see if container ships end up having to resort to similar measures as transits continue to be restricted due to the ongoing severe drought.

Article I just read says they score EVs higher because of regenerative breaking. 87-91% go to the wheels. In any case, very efficient.

https://www.motortrend.com/uploads/2022/08/Screen-Shot-2022-...

I think they are referring to energy efficiency. If I remember correctly gas cars lose about 80% of their energy propelling you forward but EVs only lose about 10-20%.

My numbers might not be exact but that’s the general range.

They have an answer to your last question in the FAQ

  When did you notify Apple?
  We disclosed our results to Apple on September 12, 2022 (408 days before public release).

Sounds roughly right. Though not all of us were full time on it at all times. We also paid that just once about two years ago. It has been part time feature and maintenance work since then.

Now run that same estimate assuming we saved 600 engineers only 1 hour per week (a very conservative number by our research and feedback). $120/hr * 1 hour saved per week * 4 weeks * 600 engineers. We paid it back in less than four months, conservatively.

I wasn’t sure if that was a lot. It sounds like a lot. But the linked article says it is the equivalent of the pollution of 73 cars in a year per launch. That actually doesn’t sound too bad?