Comments lie. What's worse, AI trusts the comments and apparent logic (inferred from identifiers and whatnot) more than the actual logic. You can quickly get into a mess of stale comments. What's worse, the LLM can…
Kimi K3 is slightly better at this. I'm using it via oh-my-pi. Can definitely sound like it's trying to be clever, but I found it less than Claude.
"Angry" version is clearly 1-to-1 ai output. I think I prefer dontbeameatproxy
> Build a one-page site for a neighbourhood coffee shop: opening hours, the address, a short menu and a photo. Nothing on it changes unless I edit it myself. If that's the entire prompt, it's quite depressing how much…
Working on a language related app makes me realize that all these supposed language models don't have many good language benchmarks
Seems like pro 0813 is exclusively served by Deepseek themselves at the moment so I wouldn't say that's the case?
Being the "regex guy" at work was also my thing. I was even in the process of making a regexr-like extension for vscode, but right about then everyone jumped ship to AI and making vscode extensions kinda felt like a…
Before the AI craze, I'd gotten quite good at writing regexes. Regexr was quite useful for decoding and composing them. I feel like they're going to become a lost art.
In my limited anecdotal experience, Kimi K3 is a bit better than Opus 4.8 and Qwen3.8 Max is disastrously bad. It can reason fine, but the moment it tries to do something it gets stuck into long second-guessing loops…
This looks pretty cool, but I'm pretty sure my imported sens from Deadlock has gone wrong. I have 0.68 in game and it feels significantly slower on the app.
This is exactly my vision. I can barely get AI to output my code how I want it to after hours of planning and refining. If you think you can be "specific" enough for AI to match your "creative vision", then maybe you're…
At least one! We might even get two.
I already thought the deal was bad to begin with, but if you look at the numbers like this it feels even more catastrophically bad, damn. This is not even considering they basically bought all the PR issues that came…
Not surprised to see this is common. At my company basically everyone and their mother are using Claude Code via Bedrock, despite us having company-wide Windsurf, Copilot and ChatGPT Enterprise accounts
You should try some of the newer OLED panels. They're all glossy and look really good.
I'm just hoping they make figuring out contactless payments a priority.
tailwind is very much not a problem for accessibility? if your content is semantic and you add the appropriate aria tags, whether or not you have 300 classes or 1 will make no difference for screen readers
It's literally just vscode? I tried it the other day and I couldn't tell it apart from windsurf besides the icon in my dock
Interesting. I haven't investigated, so I don't know where the 40mb comes from.
Don't get me wrong. 5mb is a lot for this, yes. This app, coded with love and interest could easily be made under 1mb.
Seems like you are part of the first group then, not the second. The fact that you are interested in learning and are using it as a tool disqualifies you from someone who has little clue and just wants to get something…
40mb is way too much for a JS bundle... Even with a framework you could do this with 5mb or less.
this would make it even closer to the dangerously similar travel planning app "wanderlog"
> it’s trying to solve a problem category that traditionally requires explicitness, not magic. i've been thinking basically this for so long, i'm kinda happy to be validated about this lol
Vehicle tax in the Netherlands is already weight-based. This is why the tax rate for EVs is higher than gas cars. The thing is that if you live in Hilversum and are able to import a car from the US, you don't mind the…
Comments lie. What's worse, AI trusts the comments and apparent logic (inferred from identifiers and whatnot) more than the actual logic. You can quickly get into a mess of stale comments. What's worse, the LLM can…
Kimi K3 is slightly better at this. I'm using it via oh-my-pi. Can definitely sound like it's trying to be clever, but I found it less than Claude.
"Angry" version is clearly 1-to-1 ai output. I think I prefer dontbeameatproxy
> Build a one-page site for a neighbourhood coffee shop: opening hours, the address, a short menu and a photo. Nothing on it changes unless I edit it myself. If that's the entire prompt, it's quite depressing how much…
Working on a language related app makes me realize that all these supposed language models don't have many good language benchmarks
Seems like pro 0813 is exclusively served by Deepseek themselves at the moment so I wouldn't say that's the case?
Being the "regex guy" at work was also my thing. I was even in the process of making a regexr-like extension for vscode, but right about then everyone jumped ship to AI and making vscode extensions kinda felt like a…
Before the AI craze, I'd gotten quite good at writing regexes. Regexr was quite useful for decoding and composing them. I feel like they're going to become a lost art.
In my limited anecdotal experience, Kimi K3 is a bit better than Opus 4.8 and Qwen3.8 Max is disastrously bad. It can reason fine, but the moment it tries to do something it gets stuck into long second-guessing loops…
This looks pretty cool, but I'm pretty sure my imported sens from Deadlock has gone wrong. I have 0.68 in game and it feels significantly slower on the app.
This is exactly my vision. I can barely get AI to output my code how I want it to after hours of planning and refining. If you think you can be "specific" enough for AI to match your "creative vision", then maybe you're…
At least one! We might even get two.
I already thought the deal was bad to begin with, but if you look at the numbers like this it feels even more catastrophically bad, damn. This is not even considering they basically bought all the PR issues that came…
Not surprised to see this is common. At my company basically everyone and their mother are using Claude Code via Bedrock, despite us having company-wide Windsurf, Copilot and ChatGPT Enterprise accounts
You should try some of the newer OLED panels. They're all glossy and look really good.
I'm just hoping they make figuring out contactless payments a priority.
tailwind is very much not a problem for accessibility? if your content is semantic and you add the appropriate aria tags, whether or not you have 300 classes or 1 will make no difference for screen readers
It's literally just vscode? I tried it the other day and I couldn't tell it apart from windsurf besides the icon in my dock
Interesting. I haven't investigated, so I don't know where the 40mb comes from.
Don't get me wrong. 5mb is a lot for this, yes. This app, coded with love and interest could easily be made under 1mb.
Seems like you are part of the first group then, not the second. The fact that you are interested in learning and are using it as a tool disqualifies you from someone who has little clue and just wants to get something…
40mb is way too much for a JS bundle... Even with a framework you could do this with 5mb or less.
this would make it even closer to the dangerously similar travel planning app "wanderlog"
> it’s trying to solve a problem category that traditionally requires explicitness, not magic. i've been thinking basically this for so long, i'm kinda happy to be validated about this lol
Vehicle tax in the Netherlands is already weight-based. This is why the tax rate for EVs is higher than gas cars. The thing is that if you live in Hilversum and are able to import a car from the US, you don't mind the…