fullstackchris

Comments like these are so prevalent and yet illustrate very well the lack of understanding of the underlying technology. Neural nets, once trained, are static! You'll never get dynamic "through-time" reasoning like you can with a human-like mind. It's simply the WRONG tool. I say human-like because I still think AGI could be acheived in some digital format, but I can assure you it wont be packaged in a static neural net.

Now, neural nets that have a copy of themselves, can look back at what nodes were hit, and change through time... then maybe we are getting somewhere

I've written (and am writing) extensively why I think AGI cant be as bad as everyone thinks, from a first principles (i.e physics and math) standpoint:

https://chrisfrewin.medium.com/why-llms-will-never-be-agi-70...

Still have like 2-3 big posts to publish.

Long story short its easy to get enamored with an agent spitting out tokens out but reality and engineering are far far more complex than that (orders of magnitude)

Cursor (Claude behind the scenes) can do that, however as always, your mileage may vary.

I tried building a whole codebase inspector, essentially what you are referring to with Gemini's 2 million token context window but had troubles with their API when the payload got large. Just 500 error with no additional info so...

I still don't see how AI replaces the understanding of what a server is, what DNS is, what HTTP is, or what...

I could go on and on.

Copy paste is great until you literally dont know where you are copy and pasting

Surprised this passive agressive comment is not further downvoted. Doesn't add to the conversation.

Anyway, OP has a point. I hate traveling on the same day everyone else plans to due to some holiday gap / bridge / whatever.

Agreed, in Switzerland this idea of "stretching" is common but I find it stupid. Weather going to be bad? Doesnt matter, I can stretch my total time off 3 days more!!! Total off season to where I am traveling to? Doesnt matter, I get that single extra "bridge" day! Man so cringe.

I don't know, seems much easier that if you dont want to work then don't!

I mean the tool OP posted recommended 2 weeks off at the end of March into April on the easter holiday (because of the friday and monday holiday)... who is honestly doing that?

This topic has always rubbed me the wrong way I think because its way too closely tied to the whole workaday / "work sucks" / ratrace / 9-5 mentality.

One other thing as I continue my rant, related, the whole "plan your holidays for the next year so we can figure out the resource planning, even if you move your holiday!" Ugh so depressing, I always am like "welp next year is planned already and its only November". Nothing spontaneous, nothing interesting.

Anyway, I realize also I am likely in the minority here, HN folks will do anything for a "hack".

YES! This is the post I have been looking for all my life to point to when all the "enums are a bad pattern" folks come out of the woodwork. I've never understood why people think that - I mean, why would so many languages have enums in the first place if they were "bad". Anyways, great post!

I started writing a book along side of every video course I make. (I make educational software videos, and discovered that some really enjoy the written version apposed to video - even for software!)

I just use LaTeX with some fancy packages:

https://github.com/princefishthrower/dev-book-template

I too think there can always be more long format literature out there, in a world seemingly dominated by short articles and tweets

> It does seem very likely that the Republican Party will govern the US for decades to come

Either you're a troll, governed by recency bias (i.e. today), or not very competent in US politics. If the Democrats could get their act together even just slightly, they should have won 2016 and this election as well. How? It's simple demographics:

More and more people move to cities -> cities are typically blue -> easy for dems to get elected.

There should be absolutely no reason democrats lose so often and yet due to their incompetent antics they lose far more than they should.

Civil war is a bit of an overstatement for what would again be a bunch of clowns trying to storm the capitol

I think its a crazy assumption to assume that over 200 years of political precident (4 year presidential terms) will be overturned by someone who got less votes than biden.

Every 4 years the same stuff happens, and yet every 4 years there is a so called "paradigm shift" or "rubicon crossed", when actually, nothing has really changed. It's getting really cringe and predictable.

I too, fail to see the infatuation people have with revolution / zombie apocalypse / <insert dystopian thing here>...

But, people have been trying to predict the end of the world since antiquity so there's that

There are many, many libraries that have sections that have an almost military-level protection (protected atmosphere, security, and so on) I think humanity has done a good job in general on this front

Wow weird this didn't blow up like any other anthropic / google / openai announcement... probably because it's a closed preview? If anyone else comes here the waitlist link is here:

https://github.com/github_spark_waitlist_signup

Not sure what you mean by "complex systems tasks" but most of the leading models have helped me with writing concurrent go code just fine. Not sure if that counts as "complex" enough. However this was prompting, not completion. Obviously I expect something like copilot to pick the normie non-concurrent implementation

I'll give you that! Too much of this stuff is sold as the "magic wand" solution... I guess marketing for many products has been like that for a long time...

Lots of people. For certain types of software (ISO) they are required.

But I'm in the boat (and also experienced many times first hand) all those tests you write will by definition, never test against that first production bug you get :)

Testing well is both an art and a science, and I mean, just look at the dev community on the topic, some are religious about TDD, some say unit tests only, some say the whole range to e2e etc. etc. hard to have good training data when there is no definition of what is "right" in the first place!

Finally found a comment down here that I like. I'm also with the notion of tests and also iterating until you get to a solution you like. I also don't see anything particularly "terrifying" that many other comments suggest.

At the end of the day, we're engineers that write complex symbols on a 2d canvas, for something that is (ultimately, even if the code being written is machine to machine or something) used for some human purpose.

Now, if those complex symbols are readable, fully covered in tests, and meets requirements / specifications, I don't see why I should care if a human, an AI, or a monkey generated those symbols. If it meets the spec, it meets the spec.

Seems like most people in these threads are making arguments against others who are describing usage of these tools in a grossly incorrect manner from the get go.

I've said it before in other AI threads that I think (at least half?) of the noise and disagreement around AI generated code is like a bunch of people trying to use a hammer when they needed a screwdriver and then complaining that the hammer didnt work like a screwdriver!!! I just don't get it. When you're dealing with complex systems, i.e, reality, these tools (or any tool for that matter) will never work like a magic wand.

It's funny too, because what New Architecture allows (direct access to native interfaces) could solve a lot of the problems with having to fight external dependency hell - you can now write your own, so there's no excuses.

But, somehow devs _still_ expect a 100% perfect DX while maintaining the ability to publish to mind-boggling different targets such as iOS, Android, and Web

¯\_(ツ)_/¯

I'm experiencing the same on mac. It's claiming that it's clicking and doing stuff, but it's not. (yes I gave it the necessary permissions)

I dont know about you, but sounds like every lazy developer I know... this must be proof of AGI! :D

To be fair, this is NOT the case with native mobile apps. There are some projects like detox that are trying to make e2e tests easier, but the tests themselves can be painful, run fairly slow on emulators, etc.

Maybe someday the tooling for mobile will be as good as headless chrome is for web :)

Agreed though that the followup debugging of a failed test could be hard to automate in some cases.

Fantastic stuff, this would be very useful in print art work I do.

For those further interested you see the issue this resolves by converting an full color image to an indexed image (often key colors, but low in total pixel count are neglected)

Love the motivation! Reminds me of the first stuff I built back in my university days.

One thing from and old cranky dev that I notice: it would seem the yml you post has redundancies: either have 4 endpoints, no payload or 4 different payloads, one endpoint (the endpoint itself can tell you what you need to do) However, from the express script it looks like you arrived at this in the final solution anyway. Not sure if I missed something though, is there a reason the API needs such a shape? Cheers!

But you're comparing apples to oranges anyway... a mathematical problem is vastly different than a q&a problem - which of course involves language which is anyway a lossy form of communication.

I'm definitely no AI hypster, but saying anything will "never" work over an infinite timeline is a big statement... do you have grounds why some sort of AI system could one day "never" work at evaluating some metric about someone? Seems we have reliable systems already doing that in some areas (facial recognition at airport boarding, for example)

Not affilliated, but if you want a large selection of _really_ good text to speech voices, check out eleven labs. Only problem is it's not cheap :/

I had to crack up when he abbreviated Ideal Cofounder Profile as ICP.

We've all lost the plot.

Can they stop with the iPad crap? I just want to see the macbook pro M4 stuff!