Rendered at 14:16:21 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
konradha 4 hours ago [-]
Every engineer who's worked with "agentic" workflows can tell that this is entirely generated with very little tweaks. It's embarrassing.
stephantul 3 hours ago [-]
Even the title is a Claudeism, it makes me sad
adityashankar 5 hours ago [-]
For people that are like me : This entire text is AI generated, i feel weird reading it personally, i guess others may not
embedding-shape 5 hours ago [-]
Don't tell me you don't enjoy and learn a ton from barely coherent nuggets like this?
> The most important thing the port taught me: if you can avoid it, don't. I decided to do it anyway, so here are the problems I ran into and some insights of my own, trimmed down to five. Each item is tagged with which side it hurt: quality (CORE) or performance (MFU). The first is the bug that fooled us the longest.
Chris2048 3 hours ago [-]
TBH llm generated text is usually better than this..
embedding-shape 3 hours ago [-]
TBF it kind of depends on what weights you end up using, the quality gap can be pretty wide.
attila-lendvai 4 hours ago [-]
he's just dogfooding us all...
sciences44 5 hours ago [-]
Nice work. Regarding your first insight, that's a sneaky one ^^. I experiment a similar issue with fine-tuning a small model with MLX. It was very hard to find out.
> The most important thing the port taught me: if you can avoid it, don't. I decided to do it anyway, so here are the problems I ran into and some insights of my own, trimmed down to five. Each item is tagged with which side it hurt: quality (CORE) or performance (MFU). The first is the bug that fooled us the longest.