isqueiros

To someone uninformed, how does this compare to Ghostty?

I guess the rule is kept intentionally ambiguous as to test what each person thinks should pass.

I personally answered "not breaking the rule" to emergency vehicles and second-guessed the skateboard and bike ones.

If I were to rephrase the rule, I'd write it as "No motorized vehicles in the park unless for emergencies". This way you have less ambiguity for justification.

This would be true if Gemini didn't already have some surface level access with Google maps. They just stopped short of supporting the feature I cared about

I would literally never let an AI plan my trip. I do have very specific interests though and it's nice to have an overview of suggestions of places to go.

Plus, it's great at researching the history of places you're visiting, so you can find cultural experiences a bit easier.

I don't travel often, but I do live in Europe where it's easy to visit a new city or country in the weekend. This makes this functionality a quite common use for me.

Since you're a googler, can you trigger some internal process to improve the connection between google services?

Gemini cannot create "my maps". I like creating a map of stuff for travel and now I ask it to create an importable file (which it doesn't always get right) but it should honestly do that itself.

And I don't mean that from within the Gemini app, I'd like a shareable list of places, which you can do via a very outdated maps UI

I mean this specifically for general tasks, like personal research. Small stuff. I was asking for espresso machine recommendations and it literally came up with a non-existent machine that supposedly met all my requirements. I've never seen that with ChatGPT, Claude or Kimi. It's quite surprising how it did that _after_ doing a Google search.

I'll use this opportunity while it's still early to share my experience with Argon.

I got it via the "Pro" plan, exclusively for personal task usage. So no agentic programming.

For starters, the limits are dreadfully low. Five messages on medium is already enough to trigger a 4 hour cooldown. Secondly, the best part is the integration with Google search and Maps. Makes it seamless for trip planning. Lastly it's the only "SOTA" model in a long time that has actively hallucinated details. I don't know if it's because the Gemini harness is not asking it to verify information, but I've had some real Deepseek V3-like lies in responses.

Either way, I find it difficult to get invested in Gemini because nobody will have access to Carbon for a few months anyways.

That is unfortunately a huge downside.

Huh. That would actually annoy me because speculaas and speculoos are two different things.

> Someone needs to step in before this gets wildly out of control. This sounds like a paid bot, lmao.

I wonder how much is actual improvements in the model and how much comes from better harnesses. I'd be willing to bet that the combination of better harnesses + the models being trained around agentic workflows (i.e the harnesses) has made it significantly better in many things, but it's hard to find other improvements imo.

I think that's going to be exactly the same with AI.

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 alike these all look. I appreciate some of the details from the Opus 5 version, but I can't help but strongly feel the AI vibes emanating from that design.

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 last years thing.

They really are a "tool for the job" type thing, and I've seen the abuses people put them through. The fact that we struggled to know when to reach for it before worries me that this will be exacerbated now that we don't even read our own code.

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 with no progress. It sometimes refuses to try and debug a problem even after multiple suggestions. I'm sticking to K3.

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 not really creative.

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 with Blizzard.

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.