Viewing profile — shtack

There are a large, and increasing, number of LLM-written comments on HN. If you're one of the people running these bots I have two questions for you: 1. Why? I assume most of them …

I’ve actually found that I’m able to process two speech streams and one music stream independently from those. At least for me, music seems to have a dedicated sub-processor of sor…

With reasoning on I found E4B to be solid, but E2B was completely unusable across several tests.

Really easy: don't argue on the internet. The approach has many benefits.

Strong disagree. My personal number has also leaked and I get 5-10 cold calls per day. They call during important work meetings. They call during dinner with my family. They call w…

Canadian here using y'all every day. Might as well make it the formal English plural.

The instances of that happening are likely the LLM failing to call the engine for whatever reason and falling back to inference.

I’d bet it’s using function calling out to a real chess engine. It could probably be proven with a timing analysis to see how inference time changes/doesn’t with number of tokens o…

With a dedicated GPU and some cleverness it can be relatively quick. I split the response on punctuation and generate smaller clips in a pipeline. I haven't taken the model apart t…

The model doing the heavy lifting is https://github.com/Rudrabha/Wav2Lip Mic permissions on mobile are tricky, which might have been your issue? Note in this prototype you also nee…

Cool, I built a prototype of something very similar (face+voice cloning, no video analysis) using openly available models/APIs: https://bslsk0.appspot.com/ The video latency is def…

This was my undergraduate "thesis" project. We built a GDB plugin that would generate a puredata audio structure to help with debugging. Eg. it would play snoring during a sleep() …

I have a lot of examples but a funny one that comes to mind is: in the early 2000s when IM clients were all the rage, I wrote a VB6 application to go through my MSN Messenger logs …

Also, at least the last time I checked, the Google Maps API was exorbitantly expensive. Niantic would likely get a discount, but avoiding this exploit doesn’t override all of the o…

Fair. At the current rate, the revenue takes two years to cover the original cost. The net profit takes 6. The margins are quite good due to consistent price increases.

Similarly the Canadian province of Ontario leased it's only toll highway for 99 years to an international group, for an amount it currently earns in tolls every ~2 years. Fun.

In case the devs are reading, the documentation link from the Github description is broken ( https://bulma.io/documentation/overview/start/ ), but https://bulma.io/documentation wo…

I tried so hard earlier this year to move back to FF from Chrome. I actually found the desktop experience great but the mobile app on iOS was so clunky, and I rely enough on sync, …

I think the misleading aspect in this case is that when looking at the 800k view, it seems that CO2 levels have doubled (or more) compared to previous peaks, whereas it's actually …

I run/ran a website where you could shop on AliExpress using crypto and advertised it as the only legitimate crypto website around. I had universally positive reviews but made low …

there’s a relevant xkcd, as usual: https://xkcd.com/2682/

“Consistent” UX is often one of the downsides of cross platform frameworks. Android and iOS have distinct UX details that users expect in their apps.

This is click bait. Nordstrom just announced in March that they’re closing down all of their Canadian stores, most of which are in high end neighborhoods, and I highly doubt this i…

Eleven Labs is the best I've found for speech, not sure about singing. Open to alternative suggestions.

Probably both, depending on which developers you compare against and how you measure productivity. Keep in mind there's an entire world of development where productivity is measure…