I do not know anything about Swift and iOS. I prompted a fully fledged Podcast Player App in iOS in 3 hours. Wow. https://owehrens.com/the-return-of-product-and-requirements-development-writing-software-without-being-a-developer/

Turns out inference on the cpu is not as bad as I thought. Bringing up my RAM to 128 GB is on the way. #llm

Blog post: Whisper on Apple Silicon with MLX vs RTX 4090: https://owehrens.com/whisper-nvidia-rtx-4090-vs-m1pro-with-mlx/

TIL: in #NTP there is a file accounting for leap seconds. On my server the clock is behind 27 seconds (aka 27 leap seconds). I can't get it to work and oauth tokens complain that they are not valid yet ...

Mojo🔥on Apple Silicon. Llama2.mojo up to 960 tokens/sec. This will be an interesting evening today. https://www.modular.com/blog/mojo-is-now-available-on-mac

I'm working on a podcast search product. Which podcast do you listen to? Which ones you would like to be searchable or otherwise usable with a transcript? #follwerpower
@podpodgogo
#firstscreentobeshared #backenddevloperux

Semantic search with cosine similarity. Models from huggingface.co are really nice to work with.
https://owehrens.com/semantic-search-with-cosine-similarity/ #cosine #semanticsearch @huggingface

About to build a Machine Learning PC. Any advice? Things I should take care of? GPU will be 4090.

More OpenAI Whisper Benchmark fun. Nvidia Tesla T4 and A100 https://owehrens.com/openai-whisper-benchmark-on-nvidia-tesla-t4-a100/ #nvidia #openai #whisper #benchmark

@ewolff Happy Birthday 🎂🎉🎁