Sphax

I built myself an iOS app for calorie/sodium/blood pressure tracking, meal prep planning. The main interface is a chatbot backed by an LLM.

I tell it "tonight i'm eating 150g of rice" etc, it computes calories based on the CIQUAL database (or it estimates), logs it. I set a daily goal and it helps me keep on track.

Over time, I've added the sodium and blood pressure tracking after my doctor mentioned I might have hypertension, so now it helps me keep my sodium intake in check.

And finally I've added meal prep planning: I can scan the barcodes of everything I buy and it can prepare meals that comply with my daily goals. To be honest that one is good in theory but right now I don't have the discipline to scan everything.

That's the biggest impact for me I think.

Røsdal doesn’t sound like the kind of person I want in charge of my browser.

I’m using Nono in my own coding agent, spawning a new confined process per run of my agent loop. It works fine but I had to use nono wrap because the SDK do not ship the builtin profiles which was a little annoying.

I'm not looking forward to playing vibe coded games, but yes I feel like models are good enough today to write small scoped games. I used Sol and GLM 5.3 Flash to produce a prototype of a tower defense game for myself, and it works just fine.

I _am_ looking forward however to game developers using AI to debug and optimize their games. Let's squeeze all the performance we can get from existing hardware.

This is an ad for their product, to solve a problem they created themselves that anyone could have seen coming from a mile away. Not sure this is a wise choice.

Anyone using this for their own personal email ? I'm also somewhat confused about the enterprise version, it's only a license and you're still responsible for self hosting it ?

I largely have the same feeling: I used to love it but today it's hard to justify coding by hand still. Even for my personal projects I no longer code by hand.

But it's not all bad because with an agent I'm able to achieve much more. I loved debugging an issue and diving deep but an agent with access to observability data and the code is so so much faster that it makes no sense to _not_ use one. I always wanted to have sophisticated debugging/introspection tooling at work but it nevers get prioritized; now it's doable by an agent almost autonomously. And the same goes for performance and profiling: point an agent at pprof for example and you can test all kinds of stuff without lifting a finger.

However I agree about "the zone", working with agents doesn't feel as good as working by hand.

Nothing is attractive about AI art like shown in the article

I use Opus 5.5 daily at work and a mix of GLM 5.3 (Flash or not), Deepseek v4 (flash or pro) at home and while Opus 5.5 is more capable, in my opinion it matters for less than 5% of the work i do. These chinese models are simply good enough for the vast majority of tasks I run and when they're not I use Astra or Opus 5.5. Yes, leaving Opus 5.5 on all the time is comfortable when you pay the 90€ plan but it's just not necessary.

Is this site blocking users coming from HN or something ? I'm getting a garbage page starting with "Face, those cold eyes, and the pale people; I like them if we have."

> Ecosia also has concerns about whether Mistral aligns with its environmental goals, given the large share of nuclear power in France’s energy mix and questions whether it guarantees European independence. “The fact that Mistral relies on investment from international investors is, in our view, not truly sovereign,” Kroll said.

What a ridiculous thing to say when France is among the lowest CO2 emitter per kw/h. And rambling about independence when you’re going to depend on Chinese models, it all sounds hypocritical. Just say you’re not satisfied with the quality of Mistral’s models, which is a defensible statement but don’t bullshit us.

Can't load the page but hopefully it's on an endpoint sitting behind my Tinyauth protection.

Got my hopes up when it said widely available GPUs that it would be open weights but it doesn’t seem like it sadly

Both can be true though. I had the max coding plan since january and I kept using with Pi since then, even though it wasn’t as good as opus until glm 5.3. It definitely can be a daily driver if you don’t want to use Anthropic or OpenAI. It’s going to be even better with native vision now available. And i’m not messing with my setup either.

It depends on your card I think. I can say that with a 3080 Ti and now a 5090 I have no issue playing almost all the games on steam on Fedora 44, event a lot of games not explicitly compatible. I’ve been using Linux only for probably a year now and I don’t see a good reason to go back to Windows for gaming myself.

Looks cool but it doesn’t have Reminders, just like Sol which i’m currently using. It’s the only thing that i really miss from Raycast, seems like not a lot of people used that feature ?

what are my options if i want to use a router like this ? who provides one ?

> we've been able to automatically aggregate context from pi sessions

what do you mean by this ? do you rewrite the context in your proxy ?

That is some insane value. I've been using GLM Coding Plan Max with GLM 5.1 for a while and i've tested DeepSeek V4 Pro maybe for 3 weeks now and I found it to be better than GLM 5.1 for complex coding tasks. I've used 65m tokens and with that price it cost me $1.5, that's really cheap.

We run Harbor and mirror every base image using its Proxy Cache feature, it's quite nice. We've had this setup for years now and while it works fine, Harbor has some rough edges.

You’re either trolling or simply unaware but Steam and Proton allows you to run quite a bit of the Steam library on Linux with good performance.

Love this. Great UI and straight to the point. Thank you for sharing.

One thing I'm curious about, is there a way to add a bookmark from a browser on iPhone ? When I'm browsing I often want to save an article in my reading list, right now I'm using Notion with the Share feature. Curious if you had the same need.

This is really cool. How much would that cost in Claude API calls ?

Oh I didn’t realize it was open source.

The wording « We help you setup Firecracker VMs » made me think it was a SaaS at first but maybe I was mistaken. Is the idea that a community should host its own instance of shellmates ?

This is a cool idea. I also like the website, very clean looking, congrats.

I do have some questions: can the owner of a server split it any way they want ? For example if I have a 64 GB server with 16 cores (something OVH provides IIRC) can I split it into 32 2GB/0.5CPU VM ? (assuming firecracker can handle fractions of a CPU, I don’t know). This could make for some really cheap VM compared to even OVH’s offering.

For that matter do you only support certain types of server or can the owner choose any server they want from Hetzner or OVH ?

I watched some videos of Andreas working on Jakt some years ago but right now it seems kind of dead looking at the commit history.

Yes. I have maintained my ledger with beancount for 5/6 years now. I don’t automate downloading from my bank, it’s not worth the hassle especially now that every login requires 2FA with my phone.

But I did write an importer for the csv files my bank provides and with smart_importer I don’t even have to categorize the statements anymore (although there are mistakes sometimes). I don’t gather metrics though , I use fava to have a visual view of my books.

I usually spend half an hour per month maintaining the ledger .

Aren't they (Red Hat) one of the biggest contributor to Wayland ?

The UI looks nice but it doesn't look like there's CarPlay support unfortunately.

I don't use my car that often but when I do I want to be able to access my music library. Right now I'm stuck with Plex and Prism on iOS because other solutions are not good in that regard as far as I've seen in my testing.

Hardware wise I bought a TerraMaster F4-423 used last year for about 300€. It's a great device.

Software wise, I use Fedora Server, although if I had to reinstall now I would use AlmaLinux because I don't need the new stuff coming with Fedora Server on my NAS.