I’ve worked with flip phones for years, and I think this is the first one I’ve seen with Sailfish! I didn’t see the specs, but it’s got to be comparable to a budget Android phone to run that well. I’m curious to see more of the UX, performance, and security. How does it come to an RTOS phone running Mocor, or a smart feature phone running KaiOS?
What happened to kit homes and plan books? Rather that bring down the cost of custom design, can we bring down the cost of partially pre-fabricated, modern code-compliant homes that still resemble something traditional (not a shipping container home)?
That said, I think this is neat because I’m buying a condo and knowing what’s even possible (physically, allowed by code, etc) seems more art than science. Getting answers usually involves bringing someone on-site, and almost nothing can be DIY’d anymore (either due to permits, HOA, complexity, etc)
I love SQLite and have ran it even on networked drives with queued writes for read-heavy applications. It’s an incredibly robust piece of software that’s often cost me pennies per month to serve 100k+ monthly users. But there’s definitely a time and place for solid, dedicated database servers like Postgres.
Sent a LinkedIn request. I’m building a language-specific coding agent using Apple Intelligence with custom adapters. It’s more a proof-of-concept at this point, but basic functionality actually works! The 4K context window is brutal, but there’s a variety of techniques to work around it. Tighter feedback loops, linters, LSPs, and other tools to vet generated code. Plus mechanisms for on-device or web-based API discovery. My hypothesis is if all this can work “well enough” for one language/ runtime, it could be adapted for N languages/ runtimes.
That’s awesome! I’ve got a similar project for macOS/ iOS using the Apple Intelligence models and on-device STT Transcriber APIs. Do you think it the models you’re using could be quantized more that they could be downloaded on first run using Background Assets? Maybe we’re not there yet, but I’m interested in a better, local Siri like this with some sort of “agentic lite” capabilities.
> Do you think it the models you’re using could be quantized more that they could be downloaded on first run using Background Assets?
I first tried the Qwen 3.5 0.8B Q4_K_S and the model couldn't hold a basic conversation. Although I haven't tried lower quants on 2B.
I'm also interested on the Apple Foundation models, and it's something I plan to try next. AFAIK it's on par with Qwen-3-4B [0]. The biggest upside as you alluded to is that you don't need to download it, which is huge for user onboarding.
Subjectively, AFM isn’t even close to Qwen. It’s one of the weakest models I’ve used. I’m not even sure how many people have Apple Intelligence enabled. But I agree, there must be a huge onboarding win long-term using (and adapting) a model that’s already optimized for your machine. I’ve learned how to navigate most of its shortcomings, but it’s not the most pleasant to work with.
Neat! I’ve actually been building with AFM, including training some LoRA adapters to help steer the model. With the right feedback mechanisms and guardrails, you can even use it for code generation! Hopefully I’ll have a few apps and tools out soon using AFM. I think embedded AI is the future, and in the next few years more platforms will come around to AI as a local API call, not an authorized HTTP request. That said, AFM is still incredibly premature and I’m experimenting with newer models that perform much better.
I’m also working on agents in Swift with the AFM, just having it locally already installed is a huge selling point. I think narrowly-focused agents with good tooling and architecture could accomplish quite a bit, with tradeoffs in speed and cost. But I’m under the assumption that local models (like frontier models) will only get better with time
