Hacker Newsnew | past | comments | ask | show | jobs | submit | codybontecou's commentslogin

Interesting. Is the SpeechAnalyzer API supported on iOS?

Well, he made it to the front page so there’s that.

I hope to explore AI on edge devices and see how far it can get me.

New models like functiongemma are promising and I think we may be at a point where consistent tool calling is all we need.


Looks like your form is offline.


Their voice agent is handy. Currently trying to build around it.


I see the button to skip, but is there a way to automatically skip these sections?


SponsorBlock for desktop browsers is a way around that


I forget how bad YouTube is these days. I'm so spoiled by MPV with yt-dlp and mpv_sponsorblock_minimal. It's great.


Bad is relative. I usually don't bother with the MPV/yt-dlp combo (except for rare local downloading for backup/convenience purposes) and just let it play in the browser. Not being logged in, because I have no google account anymore. It's smooth, and plays instantly when opened in a new tab. I let it have its cookies, and don't erase them, so I get the content I like, mostly. For things I'm unsure how they'd affect the algorithm, or if they are AI-slopped music, I'm just opening them in a private window. Works for me with just uBO and some additional list subscriptons in there.


ReVanced has an integration for SponsorBlock, and SponsorBlock is also available for Firefox Android



Not yet, that I know of


This became very clear with the outrage, rather than excitement, of forcing users to upgrade to ChatGPT-5 over 4o.


Do all of these models, regardless of parameters, support tool use and structured output?


In principle any model can do these. Tool use is just detecting something like "I should run a db query for pattern X" and structured output is even easier, just reject output tokens that don't match the grammar. The only question is how well they're trained, and how well your inference environment takes advantage.


Yes they all support tool use at least.


We'll hopefully (?) end up with a local llm-layer that filters ads within our browser.

I imagine we'll have a chrome extension that recognizes unwanted content and removes the text.


More likely we will just use local LLMs period.

In just a matter of a couple of years, we went from a single, closed source LLM entirely outputting tokens slower than one can read, to dozens of open source models, some specialized, able to run on a mobile device, outputting tokens faster than one can read.

The gap between inference providers and running on edge will always exist but will become less and less relevant.

What OpenAi did is like offering accelerated GPUs for 3D gaming that nobody could set up at home, before they could.

Are we using buying better gaming experience by renting cloud GPUs? I recall some companies including Google were offering that. It took a few years for investors to figure people would rather just run games locally.

We aren't dealing with gamers here, but I think the analogy is valid.


What about markdown do you feel limits you in your writing process?

The beauty of markdown is that it’s standardized. If you find your self midway through the book and feel a need to change formats, it’s easy enough to parse and reformat.


> The beauty of markdown is that it’s standardized.

It isn't standardized. And that's the main problem.


Nothing! I was asking from the point of you that you don't know what you don't know.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: