codybontecou

vorgesterndiscuss

Can microplastics never get small enough to interact with T cells?

codybontecou

vorgesterndiscuss

Last I tried this is exposed via their sdk and can be built.

codybontecou

vor 3 Tagendiscuss

The clickable areas work on mobile as well - at least using supported clients like Moshi

codybontecou

vor 3 Tagendiscuss

... and now I'm hungry. I'd love to try this.

codybontecou

vor 7 Tagendiscuss

It’s a good reflection of my energy leve.

Sometimes I’m working within 5 projects all with 1-3 agents running. Other times I’m maxed out on one agent running in a single project.

codybontecou

vor 7 Tagendiscuss

It sounds silly but lately I've been able to hit flow states doing exactly this.

codybontecou

vor 10 Tagendiscuss

Unless you have concrete evidence via evals that SOTA is actually needed, you’re just buying into the hype.

codybontecou

vor 23 Tagendiscuss

Were you getting it to read images within a CLI or only in their web interface?

codybontecou

letzten Monatdiscuss

I’m making $1000/month off of an app that was initially a single prompt.

There’s a gold rush right now. You absolutely can turn these ideas into products.

codybontecou

vor 2 Monatendiscuss

Pay to publish your team's ai usage*

codybontecou

vor 2 Monatendiscuss

I tried to like it, but it eventually got stuck in a near-infinite loop trying to debug an extra curly bracket in an iOS app.

That and the lack of image-read support surprised me. I'm a big fan of feeding screenshots into my llm and that killed it for me.

codybontecou

vor 2 Monatendiscuss

Oh this is neat. Thank you.

codybontecou

vor 2 Monatendiscuss

What are some of the Chinese colleges worth paying attention to? Is most of the AI research coming from these colleges or are they primarily from private labs?

codybontecou

vor 2 Monatendiscuss

Which entrepreneurial sites are you browsing? I feel like I'm at a similar stage in my day-to-day.

codybontecou

vor 2 Monatendiscuss

You're devolving into the realm of "What if we tell the agent to just get it right?"

Relying on the prompt to ensure the code it writes is correct is where things fail. Types, tests, linting, etc. are deterministic tools the agents tend to respect.

codybontecou

vor 2 Monatendiscuss

[flagged]

codybontecou

vor 3 Monatendiscuss

pi vs. claude code vs. codex These are all agent harnesses which run a model (in pi's case, any model) with a system prompt and their own default set of tools.

codybontecou

vor 3 Monatendiscuss

It's a custom agent harness with on-device models and the ability to swap between models.

Basically, a "toy" app to showcase where we are with coding agents on-device.

codybontecou

vor 3 Monatendiscuss

They've been slowly cutting them off of updates and/or taking them off the app store entirely.

See Anywhere and Replit. Anywhere was the #1 or #2 app and was taken off the app store entirely before being put on and then taken off again.

Last I checked, Replit hasn't received an update on the iOS app store in over two months due to reviews denying them.

codybontecou

vor 3 Monatendiscuss

Unfortunately Apple appears to be blocking the use of these llms within apps on their app store. I've been trying to ship an app that contains local llms and have hit a brick wall with issue 2.5.2

codybontecou

Submissions

[untitled]

Show HN: Health.md - Apple Health → Markdown

Show HN: Iso.me – Open-source, on-device iOS location tracker

[untitled]

Show HN: Health.md - Apple Health → Markdown

Show HN: Voicescri.pt – generate code hands-free with voice agents (BYOK)

comments