Hacker Newsnew | past | comments | ask | show | jobs | submit | gcanyon's commentslogin

How to build and deploy web apps. I worked as a developer for many years (before becoming a product manager), but always in desktop apps. I still code for fun, but I never made the jump to web apps. Now with AI that's easier than ever, so I'm going to do it.

Python. I played around with it three years ago, and did about 30 Project Euler problems with it, but I've let that lapse. I'll work to pick that up.

I bought my wife a learn-to-draw kit for Christmas, but it's really a gift for both of us.


When our kids were little we got them a wire bead rollercoaster, something like: https://www.ebay.com/itm/304637213979

It's one piece. Cleanup is picking it up and putting it where you want it. For playability, that thing kept each of our kids occupied for an unreasonable portion of their toddler-hood. We then passed it on to friends, and it did the same for their kids. They kept it, and gave it back to our kids when they had kids, and it's still delivering joy.


That's where the in:anywhere search is your friend. It searches all mail.

What I mean is, the mandatory spam filter was so braindead it sent a reply to my own message to spam, which is itself absurd, but even moreso because the other party was also using Gmail

I'll point out that I read Steven Brust's Vlad Taltos series, which started in 1983, is projected to run to 19 books with 17 done. Brust is 70, but he appears to be in reasonable shape, and the books have been pretty regular of late, so it looks like he'll finish.

I also read the War Against the Chtorr series by David Gerrold. That also started in 1983, but the last published book, the 4th of 7, came out in 1993. Gerrold being 81, despite his claims for almost a decade that books 5 and 6 are near completion, I am confident I will not see the end of the series written by him :-(


> the books have been pretty regular of late, so it looks like he'll finish.

That was true for GRRM twenty years ago, but not today.


I wish george martin took care of his health. Surprised to see Gerrold mentioned here! I read The Man Who Folded Himself a long time and it is the first fiction book I ever had the pleasure to read where all characters were the same person

I haven't read that, I'll look it up! <spoiler> Have you read By His Bootstraps and All You Zombies by Heinlein?

Would it kill them to use the words "AI coding agent" somewhere prominent?

"MiniMax M2.1: Significantly Enhanced Multi-Language Programming, Built for Real-World Complex Tasks" could be an IDE, a UI framework, a performance library, or, or...


It's not an AI coding agent. It's an LLM that can be used for whatever you'd like, including powering coding agents.

That reinforces OP’s point that it isn’t clear from their wording. I initially thought it was a speech model, then I saw Python, etc., and it took me a bit more reading to understand what it actually is

HA! I almost added a disclaimer to the original message that I wasn't certain in my identification, hence the request/complaint that they didn't make it clear. But I figured the message would be more effective if I "confidently got it wrong" rather than asking, so I went with it.

Some sad irony: just like saying the wrong thing is more likely to get you a reply, using a poor title gets them more engagement.

Maybe :-(

its main Chinese competitor GLM is like making 50 cents USD each in the past 6 months from its 40 million "developer users", calling your flagship model "AI coding agent" is like telling investors "we are doing this for fun, not for money".

The other reason being that Russian (and other non-English) speakers are usually picking up their third or fourth language, while for English speakers it's almost universally number two, and half-hearted at that... (I say that as a native English speaker whose Spanish is muy mal).

Russians don't actually speak foreign much, a Russian person who speaks four languages is considered very smart / having too much free time for their own good / both. Definitely not West Europe levels of language prowess.

Technically at least one foreign language is required as part of basic school education in Russia. For most people my age and younger it's English. Now the problem is, the quality and methods of this leave a lot to be desired. I myself learned English mostly by spending too much time on the internet and playing games that weren't translated. Other people are much more lazy.

Two years of a foreign language were required in my K-12 schooling; I took Spanish; estudio dos años, pero requerdo poco o nada. mi español es muy mal :-(

If Apple offered a reasonably-priced laptop with more than 24gb of memory (I'm writing this on a maxed-out Air) I'd agree. I've been buying Apple laptops for a long time, and buying the maximum memory every time. I just checked, and I see that now you can get 32gb. But to get 64gb I think you have to spend $3700 for the MBMax, and 128gb starts at $4500, almost 3x the 32gb Air's price.

And as far as I understand it, an Air with an M3 is perfectly capable of running larger models (albeit slower) if it had the memory.


You’re not wrong that Apple’s memory prices are unpleasant, but also consider the competition - in this context (running LLMs locally) laptops with large amounts of fast memory that can be purposed for the GPU. This limits you to Apple or one specific AMD processor at present.

An HP Zbook with an AMD 395+ and 128Gb of memory apparently lists for $4049 [0]

An ASUS ROG Flow z13 with the same spec sells for $2799 [1] - so cheaper than Apple, but still a high price for a laptop.

[0] https://hothardware.com/reviews/hp-zbook-ultra-g1a-128gb-rev...

[1] https://www.hidevolution.com/asus-rog-flow-z13-gz302ea-xs99-...


Yeah, I'm by no means saying that Apple is uniquely bad here -- it's just an issue I've been frustrated by since the first M1 chip, long before local LLMs made it a serious issue. More memory is always a good idea, and too much is never enough.

You can get any low spec laptop that has no soldered DIMMs and just replace them with the maximum supported capacity.

You don't necessarily need to go the maxed up SKU.


Would that be unified memory? Where the gpu and cpu can share the memory? Which is key for performance.

Right, no, it wouldn't, I appreciate that in this particular context my comment was entirely wrong.

Thanks for helping me see it!


No, it wouldn’t. You’d be limited to using the CPU and the lower bandwidth system memory.

The framework desktop will get you the 395+ and 128gb of ram for 2k USD.

The trick here is buying used. Especially for something like the m1 series there is tremendous value to be had on high memory models where the memory hasn't changed significantly over generations compared the cpus and even m1's are quite competent for many workloads. Got a m1 max 64gb ram recently for I think $1400.

I think pricing is just one dimension of this discussion — but let's dive into it. I agree it's a lot of money. But what are you comparing this pricing to?

From what I understand, getting a non-Apple solution to the problem of running LLMs in 64GB of VRAM or more has a price tag that is at least double of what you mentioned, and likely has another digit in front if you want to get to 128GB?


it's astonishing how apple gouges on the memory and ssd upgrade prices (I'm on an M1 w/ 64Gb/4Tb).

That said they have some elasticity when it comes to the DRAM shortage.


They gouge you on RAM and SSD but provide a far better overall machine for the price than Windows laptops.

Some tumor types metastasize well, others not so much. But the article doesn't say anything about metastasis, or leaving any cells behind from the target. Rather, it talks about destroying the targeted cells entirely, leaving behind only proteins.

> the second programming language everyone needs to know

Do they though? I've been writing SQL for over twenty years, and my experience is that LLMs have been better at writing it than I am for at least most of 2025, for most use cases. I have zero doubt that I will only be writing SQL when I want to for fun no later than sometime 2027.


People who don't already know it still need to learn it if they wanna manage LLMs writing it. Anything else is reckless. So the original point stands.

Agreed with that. As with writing SQL by hand you have to be very specific with instructing an LLM. There are many ways to get to a solution in SQL all present different tradeoffs and corner cases. I found that people that don't understand SQL and the basic of a given schema produce garbage both by hand and with LLMs

An LLM can respond to any online discussion about <x> is a good approach for solving a particular class of problems with LLMs can do <x> better than a human better than you.

> I've been writing SQL for over twenty years, and my experience is that LLMs have been better at writing it than I am for at least most of 2025

Wow, bad career choices?


I wouldn't think so, knowing SQL has been a benefit, and knowing how to use LLMs to write SQL even more so.

> see what they care

That's why you need smart people who care planning things. Miss out on either of those and you're going to fail. And right how we have people "planning" things who are neither smart nor caring.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: