Viewing profile — stealthcat

Marketed as “multimodal” but actually texts and images. Multimodal dataset should be multimedia: text, audio, images, video, and optionally more like sensor readings and robot acti…

This worldly life is no more than play and amusement. But the Hereafter is indeed the real life, if only they knew. [1] Know that this worldly life is no more than play, amusement,…

Unitree is better than Optimus. Qwen et al is better than Grok. BYD is better than Tesla.

Did you have some small toy experiments to prove this?

Should list most of the technical debt accumulated so far and rank them. At this stage, lots of corners have been cut.

Are there decent wind models and motor models if you want to model drones

Imagine all those millions of $$$ GPU of cloud credits for training, only to overlook this bug

Consider applying PhD program to some ML labs in Europe other than UK and France, they pay livable salaries like junior engineers. Better if in Swiss since the salaries are much hi…

Eat lutein supplements and get as much sunlight and barefoot grounding

Kotlin Multiplatform.

In ML the problem is passing 0D scalar tensor as 1D 1-element tensor.

How do you trust numbers to “quantify extremely smart people”? Interviewers know to hire/no-hire within first 10 minutes of talking to candidates. Similarly, the best LLMs nowadays…

More like GodotDesktop

Fun exercise… but for such use cases, people use Casadi and DrJit https://github.com/casadi/casadi https://github.com/mitsuba-renderer/drjit DrJit is made by same author of pybind1…

Multi-modal LLM like PaLM, GPT4, MiniGPTv2 relies on data encoder (image, speech models) to map data to token embedding space. Is there any attempt to directly train on file bytes?…

Isn’t this more of symptom of modern western values? Try a book by Muhammad Asad (Leopold Weiss), like the Road to Mecca. Every year during hajj in Mecca, there’s profound view of …

Kotlin multiplatform