This shouldn’t be a user-facing issue. The web UI should inject the account’s language setting or solve it like competitors. They’ve mentioned giving it multiple chances but it’s still not fixed.

Anthropic does the same thing but it's not problem

Paying for Wipr 2 + Filtr is still the gold standard on apple platforms imo. But it’s not open source and there are no custom block lists.

Challenger appears, one positive feedback so far: https://news.ycombinator.com/item?id=49321078

For those reading this, it does not work with Firefox (or anything not safari it seems). Wish I had looked that up before excitedly purchasing it lol but so it goes, seems like a good project so I’m considering it a $5 donation

Edit: looks like starting with ios26 they have “filtr” mode which extends more broadly to other apps but “stick to safari for best results”

Just so you know, Apple supports requesting refund for purchases that did not meet your expectations.

All good. I got filtr up, seems decent.

Appreciate the tip!

I have AdGuard DNS set up (mainly use HaGeZi lists) for system wide blocking + AdGuard content blockers to catch some web ads and annoyances that cannot be caught via DNS.

Works very well, it’s been a good long while since any ad cheapened my web experience.

Also a big Wipr fan, and generally a fan of the indie dev behind it too because it works so well. They’ve been responsive over email so you might be able to request a feature

Shot in the dark, but since you seem to know: does this work in the brave browser? I know(?) on iOS that under the hood everything is still safari so I'm wondering...

99% percent of times „I‘m trying the vital X“ is said it‘s an influencer getting paid to advertise X. Most of the times without saying it’s an ad. And this language accesses the most important good in today’s world: people’s attention.

It's a bit^W a lot insane that advertising is now so prevalent that even individual people are doing it. It really is an "Attention Economy".

I remember walking down a street in Istanbul, there were many restaurateurs saying "My friend, look at menu" (I joked after the trip "How was Istanbul? I met many of my friends there!"). Now I want to see "influencers" touting their products in the style of these restaurant touts.

That's why any attempt to ban advertising would only make it go more underground and harder to detect. No matter how strict the rules, people will find a way. Advertising is vital to competing businesses.

Yes, not every model release is reactionary to other labs. Either they had hints for the release of other models or they cut efforts in late stage testing of the models to hit these earlier release dates. There’s always some flexibility. And there’s certainly the incentive to cannibalize the news cycles for competitor models.

I could imagine pulling out all the stops to get a release over the finish line a week early if you're worried about being surpassed by another release

But doesn’t vscode’s settings.json have most if not all settings stored inside it? Should be a simple copy and paste.

Have your agent take care of it

20 years ago was 2006. The iPhone wasn’t out yet and the internet was far from how big it is today. These days GH and CF are giants that are synonymous for code storage and the domain resolution respectively. So it’s rather unlikely that these household names of the internet will go down the drain in the next decade.

!RemindMe 10 years

Next to my Claude Pro plan, I have subbed to OpenCode Go. I find the OpenCode UX much better than in Claude Code CLI. As for models, I started a few months ago with GLM 5.1 and it was solid and could archive near sonnet-level tasks. It weirdly sputtered out Chinese characters sometimes. Then I switched to Kimi K2.6, which is the Chinese model I used the most until now. It used way too many reasoning tokens (improved in k2.7). But executed Claude created plans reliably. Now I’m back with GLM 5.2 and it’s really solid (among other things it’s good at design) and I get good usage with the $10 plan. Still the Claude models have less hiccups but the Chinese models are getting really close.

OpenCode Go looked intriguing and I spent time reading their docs and pricing but didn’t purchase services. Do you think they are running it at a loss to get market share? (Probably not.) I have been happy buying tokens directly from DeepSeek (I am retired and everything I do is open source code and writing open content books (the manuscript files are available along with the source code) so I have no privacy issues). I also use FireWorks.ai to try different models. Both API services are excellent, but I may try OpenCode Go for a month or two to support the devs of OpenCode.

It's possible they are running at a loss at present. But in a recent podcast their founder said he believes inference is profitable, based on their experience serving models: https://newsletter.pragmaticengineer.com/p/opencode (search for "profitable")

This article is copy & pasted AI slop. While it’s perhaps a handy summary, the dozen em dashes and superlatives could have been removed.

Focusing on improving the inline visualization feature and Claude design, which were both recently introduced, will likely make more money and be more helpful than building an image model and competing with the very good ones Google and OpenAI have.