JLO64

Yesterday I test ran Qwen3.5-35B-A3B on my MBP M3 Pro with 36GB via LM Studio and OpenCode. I didn’t have it write code but instead use Rodney (thanks for making it btw!) to take screenshots and write documentation using them. Overall I was pretty impressed at how well it handled the harness and completed the task locally. In the past I would’ve had Haiku do this, but I might switch to doing it locally from now on.

Right now I have to wait 10 minutes at a time for the 2+ hour long transcriptions I've uploaded to Voxstral to process. The speed up here could be immense and worthwhile to so many customers of these products.

This is pretty awesome, and at a $3 price point is an auto purchase for me!

As someone else said though, hardware keyboard support on iOS is something that I would really want as I regularly use ShellFish on my iPhone with a USB-C keyboard.

Something that actually matters more to me is font support. I use nerd fonts for my zsh prompt, so an app that doesn't support them is a hard sell. Are custom fonts supported, or at least on the roadmap?

Additionally I just want clarification on your business model. Once I pay now I will get all future updates for free or might I have to pay for them?

EDIT: (Since Ghostty supports it) Does this also support showing images in the terminal via the kitty protocol?

I thought that project got turned into the animated film that got released not too long back? I got the impression JMS was done with B5 after he went back to focusing on comics again with his run on Captain America.

Definitely not my favorite episode, but I got a kick out of the similarities to A Canticle for Leibowitz during one of the segments in it.

I’ve been SSHing into my dev server off of my phone to run Claude Code while commuting, so this is a product that I would love to switch to. I can’t use the Claude iOS app due to the testing set up I have. That said I do have a couple of questions:

- Is it possible to completely disable or not use the remote sandbox features? I would never use them and would prefer my code stays on my device.

- For those of us that are using subscriptions, does it show our remaining usage? I would hate to run out of tokens in the middle of a session.

- One feature of the CC TUI I sorely missed on mobile is the ability to look up and directly reference files via “@“. Is any functionality like this planned?

- (This likely won’t affect my decision to use the service as I’ll just put it on a company card.) $20 per month for a service that runs CC on a remote machine in a convenient matter is steep but doable. Asking that same amount for a running code on my own server seems a bit unjustified, especially since this is pricier than the cost of a Claude pro subscription. Are there any plans to offer a cheaper tier for those of us that just want to run this on our own machines?

Just tried out Handy. This is much better and lightweight UI than the previous solutions I've tried out! I know it wasn't you intention, but thank you for the recommendation!

That said, I now agree with your original statement and really want Voxtral support...

But a PC like what you’re suggesting would result in a much higher energy bill compared to a Pi if you leave it on 24/7 to use as a server.

I’ve been pretty content with Postmark but I decided to compare pricing out of curiosity.

The free tier Remails offers is pretty generous in my opinion (3k a month) and I really like when the people making a service make blog posts like this. However having the next tier up (100k a month) start at €100 is a no go for me. It’s not that I think the price is bad, it’s that for my service I expect to send only 30k per month by the end of the year. Having a smaller capacity tier would be great for small but not tiny projects.

Most people working office jobs are scared of the terminal though. I see this as not being targeted at the average HN user but for non-technical office job workers. How successful this will be in that niche I'm not certain of, but maybe releasing an app first will give them an edge over the name recognition of ChatGPT/Gemini.

I can second this. I'm an online coding instructor and within our company Replit was the website/environment we were told to use with our students. I really didn't like it due to all the AI features (I believe that when you're learning to code you shouldn't use LLMs) but the collaboration features were really good.

Unfortunately they added a limit to the number of collaborators per account and we had to stop using it.

Just yesterday I was trying to figure out a method to accurately estimate my remaining usage for the five hour sessions for a shell script. It wasn't until I pointed Claude at your repo and had it make something based off of that that I got it to work well.

Thank you!

Polska is in Central Europe tho

How new was your email address? When I set up my work Claude account with my near fresh email (I had just set up Outlook to work with my domain) I had no issues.

Supergirl and The Batman 2 are releasing relatively soon so I don’t think that will be affected much by all this. Same with Clayface since that just entered post production. It’s the movies coming after (Superman 2, Batman movie thats not tied to “The Batman”) that will be affected by all this.

My opinion of James Gunn has changed recently (especially after the ending of Peacemaker S2) but I still think he’s the best person possible to be in charge of live action DC. I really hope he keeps some form of control but I doubt it…

As someone who is currently delivering Amazon packages with their own vehicle (Amazon Flex), what’s the process like to become a mail carrier? The miles are starting to take a toll on my car, so delivering for USPS is tempting for me…

Not necessarily my favorite Christmas movie, but I always watch The House Without a Christmas Tree during the holidays:

https://en.wikipedia.org/wiki/The_House_Without_a_Christmas_...

Not a tech company, but I feel strongly about this when it comes to LAMY (a fountain pen company). As far as I can tell their pens (notably the Safari and 2000) have stayed almost exactly the same for the past 40 years!

The only thing they tweak in these pens are the limited edition colors, which for the Safari they're releasing probably 3+ per year. I once met a guy who had a collection of over 50 Safari pens so I guess that market works out for them…

Personally I prefer Fox 11's coverage of these chases. The guy they have up there is fun to listen to and always sprinkles in comparisons to past chases.

This is legitimately game changing a feature in my SaaS where customers can generate event flyers. Up until now I had Nano Banana generate just a decorative border and had the actual text be rendered via Pillow controlled by an LLM. The result worked, but didn’t look good.

That said, I wonder if text is only good in small chunks (less than a sentence) or if it can properly render full sentences.

Personally I use OpenAI models via the API for transcription of PDF files. Is there a big difference between them and Gemini models?

Just tried it out and it works perfectly! Thank you for letting me read Kobo books!!

Thank you so much!

> Personally, I've just stopped buying books from Amazon. I find that Kobo is often cheaper and their DRM is easy to bypass.

Anyone have any advice on how to bypass Kobo DRM? I can only buy ebooks without DRM (typically through ebooks.com) for my kindle running Koreader so this would be amazing.

In my product I use gpt-5-nano for image ALT text in addition to generating transcriptions of PDFs. It’s been surprisingly great for these tasks, but for PDFs I have yet to test it on a scanned document.

I second this. I hated (perhaps not consciously) being forced to read books in high school, however recently I’ve gone back and started rereading those books I was assigned and have loved it!

As someone who has never visited any of the sites in question, it would have been helpful if a couple of links or screenshots were provided.

> Crucially, it syncs feed read state between my laptop and phone.

This is via iCloud and only works for iPhones/Macs. What’s great though is that NetNewsWire also supports RSS feed aggregators (I personally use FreshRSS) so that you can sync RSS read status over all your devices, even non Apple ones!

I’ve been tempted over the years to switch to other RSS apps, but this feature is what keeps me using NetNewsWire.

I’m not familiar with TR-RSS, but I self host FreshRSS and it’s a great RSS feed aggregator I use with NetNewsWire on macOS/iOS.

My experience with Cerebras is pretty mixed. On the one hand for simple and basic requests, it truly is mind blowing how fast it is. That said, I’ve had nothing but issues and empty responses whenever I try to use them for coding tasks (Opencode via Openrouter, GPT-OSS). It’s gotten to a point where I’ve disabled them as a provider on Openrouter.