indoor47

Honestly, if I zoom on the map, I need the button "search here" and places of that area. That's still missing here. Simple, but core.

Well, it makes sense:

"Clef builds upon this concept, but uses a different base model as the backbone. We currently use Qwen as the base model and post-trained it to suit decision model use cases. "

Someone posted 50 LLM interview questions of FAANG that made the rounds. I figured instead of reading them once and forgetting, I'd build a little app to drill them.

Took about an hour with Claude Code.

It's got spaced repetition, XP, streaks, difficulty tiers, usual gamification to trick the brain into studying.

Covers transformers, attention, RLHF, RAG, fine-tuning, tokenization, etc.

No login needed, progress saves in localStorage. Optional account if you want.

Curious if the my AI-slop-in-an-hour will do smth useful or nah.

tv.garden might witness similar issues :/

Didn’t work for me.. animation just had some camera scroll, but figures remained static

This would still be a remarkable dataset for learning. And worth the storage. Though it might need other inputs as well (like pressure zone etc.) to escape potential biases.

So, do OKRs then make any sense?