Pinned Tweet
An Entrepreneur vs an Intellectual. Must watch to the end (only 55 sec) & sound is optional.
Carlos Jung retweeted
Replying to @SamCKx
I hate to be the one to burst the Wright brothers bubble today, but the spectacular “flight” we witnessed at Kitty Hawk needs a little context. The Flyer is carrying around 274kg of wood, fabric and wire, plus the weight of the 12-hp engine, propellers and pilot needed to keep it aloft.
Based on the published figures, that gives it roughly 12 seconds of maximum flight before it settles back into the sand.
In short, it’s a gimmick.
Carlos Jung retweeted
Muse Spark Open -- weights releasing today -- runs great on new Mac Studios thanks to work with @johnternus and Apple.
Carlos Jung retweeted
Terence Tao needs to be given a copy of Antifragile.
Birds take off, then some academic branch lectures birds how to fly & takes the credit for it.
Replying to @cremieuxrecueil
If you’re really with it ur conversational partner can use completely the wrong words or literally make words up nd u will still get what they’re saying bc of context clues & logical progression. And if im lucky enuf2 speak with a rly smart person I barely have to talk at at all
The probability of finding a substantially better “single Spark” daily driver in the next 12 months is high.
Carlos Jung retweeted
Replying to @teppofelin
Your brain is laundering human work and knowledge. Constantly. You didn't invent the language you're speaking.
Carlos Jung retweeted
If you get addicted to things easily, good, your problem is aim. Point that same obsession at a skill, your body, or your work for 2 years and people will start calling you "disciplined" instead.
NVIDIA is facing a pincer attack from Apple and China. Apple is advancing from the B2C side. China is advancing from the B2B side, coming for the AI infrastructure. In a pincer attack, you weaken the arms before they close. The Hugging Face acquisition looks like exactly that.
Carlos Jung retweeted
GLM-5.3-Flash streaming at 32 tok/s on a single Spark via Tensorfold ⚡️
i will share the recipe later today
Carlos Jung retweeted
tl;dr - the new Mac is VERY fast across the board for low concurrency, but scales horribly to higher concurrency on both models at this point.
Making great headway on the Mac so far, have had clankers on it since the moment I turned it on, benchmarked all inference engines and quants of Qwen 3.8 Flash and GLM 5.3 Flash for a solid baseline and am having them work on improved kernels for both models, already seeing massive improvements.
Initial findings confirm oMLX is the best engine right now for this, which is what I’m basing my optimization work around at this point.
Carlos Jung retweeted
GLM 5.3 Flash:
github.com/MiaAI-Lab/GLM-5.3…
Qwen3.8 Flash Next on solo Spark:
github.com/MiaAI-Lab/Qwen3.8…
Qwen3.8 Flash Next on 2x DGX Sparks:
github.com/MiaAI-Lab/Qwen3.8…
DeepSeek v4.1 Flash on 2x DGX Sparks:
github.com/MiaAI-Lab/DeepSee…
DeepSeek v4.1 Flash on 3-4x Sparks:
github.com/MiaAI-Lab/DeepSee…























