SilverSlash

Very good. Just look at Gemma 4.

I like the concept. It would indeed be good to have a modern component library with AI design tropes as I think the old components libs haven't caught up. But in this particular case I must say, a lot of the components here just look plain ugly.

Useful concept but missing some obvious features like filtering on availability of tool calling or support for different modalities, etc.

I really like the agentic search feature that can keep you updated. Basically an ifttt but built into google search with an LLM on top.

Was this a Tesla with HW3 or HW4? Also, was it in the US or outside the US?

I hadn't heard of TanStack but a quick look at their website doesn't inspire confidence tbh. I mean, just take "TanStack Pacer".

It provides such things as:

```

import { Debouncer } from '@tanstack/pacer' // class

const debouncer = new Debouncer(fn, options)

debouncer.maybeExecute(args) // execute the debounced function

debouncer.cancel() // cancel the debounced function

debouncer.flush() // flush the debounced function

```

Why? Just why do you need to install some "framwork" for implement debouncing? Isn't this sort of absurdism the reason why the node ecosystem is so insecure and vulnerable in the first place? Just write a simple debouncer using vanilla js...

As in, htmx is better? I haven't used it but last I looked into it I was extremely confused as to whether it was a meme, an actual framework, or both.

A lot of the LLMs are very familiar with next.js and vercel is also aggressively building an ecosystem around their tooling for LLMs. So I wonder if this problem will only be exacerbated when everyone using LLMs is strongly nudged (forced) to use next?

Nope. I've been working on this project for a couple of days now and things were mostly going well. A significant portion of the mvp backend and frontend was built and working. Then this one seemingly simple bug appeared and just totally stumped both Codex and Claude Code.

There was even another UI component (in the same file) which was almost the same but slightly different and that one was correct. That's what I copy pasted and tweaked when I fixed the problem. But for some reason the models were utterly incapable of making that connection.

With Codex and Claude Code I thought maybe because these agentic coding tools are trained to be conservative with tokens and aggressively use grep that they weren't looking at the full file in one go.

But with Gemini I used the web version and literally pasted that entire file + screenshots detailing what was wrong (including the other component which was rendering correctly) and it still couldn't solve it. It was bewildering.

That's hard to believe in my case. I tried a variety of prompts, 3 different frontier models, provided manual screenshot(s), the agent itself also took its own screenshots from tests during the course of debugging. Nothing worked. I have now fixed the bug manually after 15-20 minutes of playing around with a codebase where I don't know the language and didn't write a single line of code until now.

I understand how laughable that sounds when I say it out loud. But the reality is, when I'm in a state of 'Tell LLM what to do, verify, repeat', it's really hard to sometimes break out of that loop and do manual fixes.

Maybe the brain has some advanced optimization where once you're in a loop, roughly staying inside that loop has a lower impedance than starting one. Maybe that's why the flow state feels so magical, it's when resistance is at its lowest. Maybe I need sleep.

Someone needs to make a compilation of all these classic OpenAI moments. Including hits like GPT-2 too dangerous, the 64x64 image model DALL-E too scary, "push the veil of ignorance back", AGI achieved internally, Q*/strawberry is able to solve math and is making OpenAI researchers panic, etc. etc.

I use Codex btw, and I really love it. But some of these companies have been so overhyping the capabilities of these models for years now that it's both funny to look back and tiresome to still keep hearing it.

Meanwhile I am at wits end after NONE OF Codex GPT-5.4 on Extra High, Claude Opus 4.6-1M on Max, Opus 4.6 on Max, and Gemini 3.1 Pro on High have been able to solve a very straightforward and basic UI bug I'm facing. To the point where, after wasting a day on this, I am now just going to go through the (single file) of code and just fix it myself.

Update: some 20 minutes later, I have fixed the bug. Despite not knowing this particular programming language or framework.

I'm deeply regretting paying for this service right now. There is some gaslighting going on in that issue that it's because of the 1M context model. I am using the non-1M context model and it's still disastrously bad.

Good, we agree :)

It's amazing how pretty much every reply to my original comment has failed to comprehend that I was not criticizing globalization. Whether it's even possible to get to where we are without it is also debatable.

But the question you're asking me is meaningless, because the premise is wrong. My original reply was true and entirely independent of my or anyone else's opinion of whether globalization is good/bad.

Umm, I think you have it reversed. A helium plant in Qatar shutting down causing problems to US chip consumers is precisely because of globalization.

Interestingly, it actually regressed on Terminal Bench 2.0.

GPT-5.4: 75.1%

GPT-5.3-Codex: 77.3%

Their "API" isn't what's being accessed here. As far as I understand it's using their subscription account oauth token in some third party app that's the issue here.

Same. Cannot find it in that thread and I would like to know the source too.

What's "tfa"?

Literally in the first paragraph of Simon's post if you cared to read it:

> this has actual legal weight to it as the IRS can use it to evaluate if the organization is sticking to its mission and deserves to maintain its non-profit tax-exempt status.

Assuming lawyers were involved at some point on, why did they keep "OpenAIs" instead of "OpenAI's"?

A thing which happens to me very often: I realize I'm experiencing a very real visceral discomfort nagging at me in the back of my mind.

It happens because I will have ctrl+c'd something several minutes ago. My mind subconsciously "holds" onto the info that I have text copied in my clipboard. It's only when I ctrl+v it and consciously discard it does the nagging go away.

I have no idea why it happens or if others experience this too. But I fully agree with the author about starting from nothing and getting rid of the clutter you think isn't bother you but which you're probably subconsciously holding onto.

I've been thinking about this recently as I hear it often. Would people who want to buy a car in the Tesla price range really choose a slightly cheaper Chinese EV if those were available?

Personally I have a hard time believing this. But even if you had similarly priced Chinese options, I would guess the main reason for buying a Tesla is not just because you want an EV. While a Tesla will be a reliable baseline EV, surely the reason you (or at least I) would buy one is for the supervised self-driving feature.

This was far more thrilling and exciting to watch than I thought it would be. Which feels wrong when I say it, but I don't mean it was a good watch because of the consequences of failing. Rather because it was amazing watching a human perform at such a peak level.

I think NYT said their sources claim he was paid mid 6-figures? Which is really shitty of Netflix. If I were him I would've asked for at least $5M.

I really wish Google will flag videos with any AI content, that they detect.

I have a multitude of complaints about Tahoe, many of which others have already pointed out. One more thing that doesn't get mentioned as often but probably should is their new placement of the volume / brightness level UI which pops up when you change those two.

It used to be in the middle of the screen and worked just fine. But then someone thoughts of putting it exactly where browser tabs usually are and I _constantly_ find myself in a situation where I change the volume and try to click on a tab that this UI is on top of. Then I need to move my mouse outside the UI otherwise it stays there, and wait for it to disappear before I can change tabs. It's infuriating.

I don't know if I'd call a book with 61 chapters "concise".

Claude is cranked to the max for coding and specifically agentic coding and even more specifically agentic coding using Claude Code. It's like the macbook of coding LLMs.