I did that a lot initially, it’s really only with the advent of Claude Code integrated with VS Code that I’m learning more like I would learn from a code review.
It also depends on the project. Work code gets a lot more scrutiny than side projects, for example.
Or, given that OP is presumably a developer who just doesn't focus fully on front end code they could skip straight to checking MDN for "center div" and get a How To article (https://developer.mozilla.org/en-US/docs/Web/CSS/How_to/Layo...) as the first result without relying on spicy autocomplete.
Given how often people acknowledge that ai slop needs to be verified, it seems like a shitty way to achieve something like this vs just checking it yourself with well known good reference material.
ChatGPT: Certainly, I'd be glad to help! But first you must drink a verification can to proceed.
Or:
ChatGPT: I'm sorry, you appear to be asking a development-related question, which your current plan does not support. Would you like me to enable "Dev Mode" for an additional $200/month? Drink a verification can to accept charges.
A little hypothesis: a lot of .Net and Java stuff is mainlined from a giant mega corp straight to developers through a curated certification, MVP, blogging, and conference circuit apparatus designed to create unquestioned corporate friendly, highly profitable, dogma. You say ‘website’ and from the letter ‘b’ they’re having a Pavlovian response (“Azure hosted SharePoint, data lake, MSSQL, user directory, analytics, PowerBI, and…”).
Microsoft’s dedication to infusing OpenAI tech into everything seems like a play to cut even those tepid brains out of the loop and capture the vehicles of planning and production. Training your workforce to be dependent on third-party thinking, planning, and advice is an interesting strategy.
This is currently negative expected value over the lifetime of any hardware you can buy today at a reasonable price, which is basically a monster Mac - or several - until Apple folds and rises the price due to RAM shortages.
$2000 will get you 30~50 tokens/s on perfectly usable quantization levels (Q4-Q5), taken from any one among the top 5 best open weights MoE models. That's not half bad and will only get better!
If you are running lightweight models like deepseek 32B. But anything more and it’ll drop. Also, costs have risen a lot in the last month for RAM and AI adjacent hardware. It’s definitely not 2k for the rig needed for 50 tokens a second
Could you explain how? I can't seem to figure it out.
DeepSeek-V3.2-Exp has 37B active parameters, GLM-4.7 and Kimi K2 have 32B active parameters.
Lets say we are dealing with Q4_K_S quantization for roughly half the size, we still need to move 16 GB 30 times per second, which requires a memory bandwidth of 480 GB/s, or maybe half that if speculative decoding works really well.
Anything GPU-based won't work for that speed, because PCIe 5 provides only 64 GB/s and $2000 can not afford enough VRAM (~256GB) for a full model.
That leaves CPU-based systems with high memory bandwidth. DDR5 would work (somewhere around 300 GB/s with 8x 4800MHz modules), but that would cost about twice as much for just the RAM alone, disregarding the rest of the system.
Can you get enough memory bandwidth out of DDR4 somehow?
Look up AMD's Strix Halo mini-PC such as GMKtec's EVO-X2. I got the one with 128GB of unified RAM (~100GB VRAM) last year for 1900€ excl. VAT; it runs like a beast especially for SOTA/near-SOTA MoE models.
Just you wait until the powers that be take cars away from us! What absolute FOOLS you all are to shape your lives around something that could be taken away from us at any time! How are you going to get to work when gas stations magically disappear off the face of the planet? I ride a horse to work, and y'all are idiots for developing a dependency on cars. Next thing you're gonna tell me is we're going to go to war for oil to protect your way of life.
Definitely. Right now I can access and use them for free without significant annoyance. I'm a canary for enshittification; I'm curious what it's going to look like.
We already had that happen. When GPT 5 was released, it was much less sycophantic. All the sad people with AI girl/boyfriends threw a giant fit because OpenAI "murdered" the "soul" of their "partner". That's why 4o is still available as a legacy model.
I can absolutely see that happening. It's already kind of happened to me a couple of times when I found myself offline and was still trying to work on my local app. Like any addiction, I expect it to cost me some money in the future
If only it were that easy. I got really good at centering and aligning stuff, but only when the application is constructed in the way I expect. This is usually not a problem as I'm usually working on something I built myself, but if I need to make a tweak to something I didn't build, I frequently find myself frustrated and irritated, especially when there is some higher or lower level that is overriding the setting I just added.
As a bonus, I pay attention to what the AI did and its results, and I have actually learned quite a bit about how to do this myself even without AI assistance
