Viewing profile — quickthoughts

Ha just wrote a post[1] about a sort of 4th option - max out cheap compute to create more tangible things that can be used/run locally. 1: https://news.ycombinator.com/item?id=4851…

what does this actually do? claude output -> drop -> app that you can't really change?

Are most corporations preformative? (yes)

I use small models like Gemma to improve transcriptions from ASR models amongst other micro-tasks. I actually built out a fine-tuning whisper pipeline with all local (smaller) mode…

I don't think this will be the case, image and video processing typically is more computation hungry, especially in realtime contexts. Apple already pegged Google as their cloud-pr…

It's everyone. Especially google, but all the big tech companies play in the same pool. Amazon, Google, Apple, Meta etc make money selling ads, which ultimate enables the tools tha…

I've been working on the flip side of this with ASR models, but the problem space is the same, conversational/real-world data is needed. Whisper often mistook actual words I say an…

Plus one for the IKEA pour over. Its cheap and functional, perfect for travel too.

VSCode with auto complete and Gemini 2.5 Pro in a standalone chat (pick any interface that works for you, eg librechat, vertex etc). The agents-in-a-IDE experience is hella slow in…