osigurdson

Back in the days of the LAMP stack, the use of Linux would have been much less obvious and thus warranted the inclusion of the "L" in the acronym. After all, leaving it out might arguably have sounded better - the AMP stack.

I don't love the appeal to romanticism portrayed in this article.

I'm unfamiliar with these stacks but including "U" / Unix seems odd. I suspect these run completely fine on Linux, Windows or macOS. Its almost like including an "E" in your stack for electricity.

I use both. Not because I am cool, but because it is cost effective for personal projects with two $20 / month plans. It is also nice to be able to see what the state of the art is like for both.

Personally, I find it very interchangeable. I open codex --yolo or claude with whatever there yolo flag is (have an alias).

I don't know how intentional it is / was, but LLMs in general just love to hear themselves talk!

I don't think it is meant to be objectively the most efficient interface. It is more about being remarkable in a Seth Godin sense. For me I just want things to be blazing fast inside the dashboard.

I've notice that as well. If you don't know how to do something having an agent with tools is great (in general, not just PH). But, its also quite slow and imprecise. I think that having the agent act more as both a teacher and "doer" is best.

It seems like an odd thing to run locally with so many dependencies.

True!

What I don't understand is, what kind of legitimate criminal would not use such techniques? Are bank robbers planning things out on iMessage? If so, presumably they won't be criminals for very long. Therefore these types of initiatives only impact the innocent and inept but still active criminals.

I don't think $4B is reasonable for an acquihire. They must see value in the technology.

Zig is really nice. I enjoy using it a lot. Glad to hear that it is getting a little more funding.

Its hard to find a middle ground between fully understanding everything in a PR vs a vibe coding type approach. Can you understand "just a little bit" of a PR and merge it into a code base you really care about? Is it maybe fine to "mostly understand it" on the other hand? Its definitely a tough call and its impossible to argue that no trade off is being made.

LLMs are perfect for quick prototypes, speed runs, learning, etc., but if the code really matters its still not clear cut. I think the definition of what "really matters" is very project dependent of course As an extreme example you would want to understand every line of the code for the control system runs an MRI machine or a jet engine since bugs might mean life or death. Depositing money into the wrong account might not kill anyone but could lead to severe economic losses. But, then again, even problems in far less consequential software may be drastically sub-economic (i.e. saving $1000 on the implementation might cost $10000 if customers aren't happy and fails to re new). Pick your scenario I guess.

The problem is, this isn't going to change regardless of how well a new model scores on a benchmark. It seems actually AGI is needed.

While I don't know, I suspect the boy's parents do not share your views. He is able to ride a tricycle and improving.

A 2nd year project back in the day was to build a 4 bit CPU on a breadboard. We had the advantage of having an ALU IC but was still quite tough to get working!

Running AI on timesharing mainframes does seem like an odd final state for the world.

Are people still using Cursor? I haven't in at least a year but perhaps I'm in the minority.

I don't think many who plan on buying the stock it to be controlled by anyone other than Musk.

I think a better metric these days is what percentage of code is not reviewed / understood by humans. That is the real bottleneck. Until we can stop looking at the code, AI barely matters - you are just trading quality for quantity.

Thats why it is so amazing for speed runs and prototypes. Here it is legitimately > 10X faster.

It doesn't help shareholders or customers in any way however so we should not celebrate it or even simply accept that this is "the way things are". It is an error to be corrected.

I'm surprised they cared enough to do this. I'd still rather use Linux but MacBook value is incredible.

They will have to open source it. Otherwise it is impossible for anyone outside of OAI to gain any insights - basically just a Boris at this point.

I'd much rather people think deeply about summarizing their work. This helps others understand it but, more importantly, helps the developer understand what they did. If its hard to summarize, maybe it should be tightened up a little for instance. Enforcing a "schema" might help a tiny bit but also can cause people to check out a little as it can feel like just another meaningless process.

Probably as good as that can get is something like WSL. Microsoft put a lot into that but still not the same as just using Linux. I wish Apple / MS would do the opposite and build their OS on top of Linux but of course that will never happen.

You may be right, its possible however that people running on Azure may use it locally for testing.

I bounce the moment I see "fascist" in your pie chart. Sorry.

It hurts, but I'll pay a premium for worse hardware that will run Linux. But for others in my family Macbooks are just far better value by a wide margin than Windows laptops. Vertical integration really wins these days.

Automated outbound is a real problem now. I think LinkedIn actually has a pretty good model in which it costs money to send a message if the other party does not reply. Lucky for them of course! Nice to be able to collect 100% of the value of a needed incentive structure!

Does containerization help much here? If it's a code tool then presumably it needs access to your code files (read / write). Maybe there are use cases for it of course.

Right. You mean all behaviors are tested, essentially.

So if you / team are going to implement a new feature, what does that look like? Do you write Gherkin or similar, unit tests or both? Can you provide an example of what that might look like? How much of this has changed for you since the pre-AI days?