mrklol

My biggest problem with web push is that you won’t get notifications on iOS anymore, if you haven’t opened the app for a while. A tad bad for some apps.

How did you give it access to your projects? That’s something I never thought does work as the voice model has no access outside of its scope?

And also the amount of people running it in thousands of scenarios. Not sure if these areas can be even tested for, but I guess time will tell (can observe Bun if it breaks somewhere as that’s afaik the first big AI rewrite which got into prod for masses).

I agree but I think from Bun we learned that a project with really good tests and enough tokens can be converted from one language to another quite good!

Why?

In which areas do you feel like the mentioned are bad? Do they find less and your own solution has more success?

If the latter, do you know why?

And the team behind opencode is working on an alternative https://github.com/anomalyco/rift

Because it’s high or low? Imo it’s not that hard to reach that amount, they have quite a few employees, offering services for ~20 years and it’s probably also containing small repos - would’ve imagined way more tbh.

Isn’t it a really cheap alternative to sota models (according to benchmarks)?

I like their approach on going smaller, X4 has the perfect size and I feel like X3 is actually even a bit too small (missing usb c is a bit weird tho).

Compared to kindles going bigger and bigger - now with 11+ I feel like they are too big as a handheld.

I think I would move everything too for my hobby projects, if it wouldn’t be that crazy cheap at Cloudflare. I still use external servers in the EU for backend stuff, but CDN, static pages, frontend projects run at Cloudflare for free or the $5 tier. I legit can’t get cheaper than this, till they adjust their pricing.

Their free tier seems way too generous and I suppose this has to be adjusted at some point.

Personally the main advantage is to simply spin up new ones with the same setup. You can also do that by yourself but imo it includes way more managing and time compared to exe

imo a question is, do you still need to understand the codebase? What if that process changes and the language you’re reading is a natural one instead of code?

Seems like they have a rate limit so it is kinda the same as normal subs - don’t really see the advantage yet

Where exactly are they behind?

Not directly 2024, there was a big update end 2025

Am I missing something? Isn’t that the language most are using currently when looking at research at openai, google, deepseek etc?

Same thought I had while reading, don’t really see a big advantage here.

Firefox mentions the following ones:

"- Translations, which help you browse the web in your preferred language.

- Alt text in PDFs, which add accessibility descriptions to images in PDF pages.

- AI-enhanced tab grouping, which suggests related tabs and group names.

- Link previews, which show key points before you open a link.

- AI chatbot in the sidebar, which lets you use your chosen chatbot as you browse, including options like Anthropic Claude, ChatGPT, Microsoft Copilot, Google Gemini and Le Chat Mistral."

Yep same, I often think why this isn’t a thing yet. Running some tasks in the night at e.g. 50% of the costs - there’s the batch api but that is not integrated in e.g. claude code

I am similar but I think we just have to adjust. Learn and improve writings specs with all the details.

Didn’t openclaw switch to vector based because it used way less tokens as it always loaded all memories? Seems way more efficient

Because they make it easy. Imagine they limit their models to their tooling and suddenly it’s introducing work.

I mean if it’s running in your lan, isn’t it local? :D

My main problem always was that I hoard these links and never read again. Now I am trying to get a short summary (via llm‘s) and it works quite well.

Looks like SES + api access, isn’t Amazon offering that already?

They also have a $20 and $40 tier.

Oh, I thought candidates got 2 hours but now I am confused too

Milk before cereals

For me it’s kinda the same. I always hated typing actual code, I love planing, reading, finding bugs etc. But writing code? Eh, I never enjoyed that. Now with agents I can kinda do exactly what I like, plan, write in natural langue and then do code review.