Viewing profile — wkcheng

If the benchmarks are real and reflect actual use, then this is an insane model. This 300B model outperforms the previous DS4 Pro preview model (1.8T params), and it looks like it …

Just use it through something like Azure. They host the entire model and serve it from the US. I'm sure that there are other providers like this. We use it that way and it works gr…

Use it through Azure! Azure hosts DeepseekV4-Pro and DeepseekV4-Flash themselves. We're using it and it works great. You don't get the discount that Deepseek is providing, but it's…

This is nice! I tried it for a bit and it was indeed quite fast. Are you looking for contributors, or are you building this as a personal tool? I ran into some issues when attempti…

This was my workflow (this is repro-able 100%): 1. Take an obsidian vault (just a few folders and subfolders of markdown files) 2. Copy the entire folder (keep all of the dates wit…

Nice work! This looks really cool. I downloaded and am trying it out, but I'm running into a pretty annoying sorting bug that's preventing me from using it for real. I copied over …

Yeah, Parakeet runs great locally on my M1 laptop (through MacWhisper). Transcription speed of recordings feel at least 10x faster than Whisper, and the accuracy is better as well.…

Does this support using the Parakeet model locally? I'm a MacWhisper user and I find that Parakeet is way better and faster than Whisper for on-device transcription. I've been usin…

Yeah, that's the way that I cut onions: you make vertical cuts followed by one single horizontal cut slightly above the cutting board. This way of calculating doesn't take into acc…

The attitude of the blog writer in their interactions also feels off. Just reading this blog post makes me think that this person is difficult to work with, requires extremely clea…

Maestro AI | Senior Full Stack Engineer | REMOTE (US) Seattle onsite preferred, Remote OK | https://www.getmaestro.ai/ Hi, I'm William, the co-founder and CEO of Maestro AI. We're …

We've been thinking about the things you need to be careful about when building AI products for businesses and put them in this article. Are there important things that we missed?

It's insane that that this works, and that it works fast enough to render at 20 fps. It seems like they almost made a cross between a diffusion model and an RNN, since they had to …

Maestro AI | Senior Full Stack Engineer, Senior AI Engineer | REMOTE (US) Seattle onsite preferred, Remote OK | https://www.getmaestro.ai/ Hi, I'm William, the co-founder and CEO o…

Does anyone know whether the 128K is input tokens only? There are a lot of models that have a large context window for input but a small output context. If this actually has 128k t…

This may be why things like Substack and Beehiiv have taken off. The only way to combat reposting through Google is to deliver content directly to email inboxes before it gets rank…

Yeah, you're right. Data breaches are essentially just slaps on the wrist to companies like AT&T. Maybe it's possible to fine them based on the proportion of the userbase that was …

I wonder if allergies can eventually be fixed somehow as well. There has to be an immune or autoimmune reason why some people have tons of allergies and other people are perfectly …

Yeah, "performed dominance" as you call it definitely is orthogonal to rationally understanding the world. The problem is exacerbated by content and replies trending shorter over t…

This is a great article on the difference between an obstinate person and a persistent person, but I'm not sure the general public perceives them the same way that Paul does. What …

This is really helpful, thanks! I have a bunch of audio that I need to clean up and this looks like it could fit the bill. Do you know if there are any license issues with this? I …

OpenAI models are great, but a lot of people have blinders on and only use ChatGPT or GPT4. There are fantastic alternatives, and there are plenty of reasons to try them out. I've …