Today, we’re excited to introduce Miso One, the most emotive voice model in the world.
Miso One is an 8-billion-parameter text-to-speech model for highly expressive speech generation. It emotes like a human and responds faster than a human, with just 110 milliseconds of latency.
We’ve open-sourced the model weights, with API access coming soon.
Hear how Miso One sounds in the thread below.
“How did you master so many different fields?”
The education system has brainwashed you into the wrong idea of how to truly learn. You need to shift your mindset.
Instead of trying to accumulate information, understand that the perfect time for you to gain expertise is at the time of execution.
The optimal learning loop will always be tackling harder and harder problems and continuously stacking the critical knowledge gained.
This comes naturally to fields such as gaming and math. You know exactly what the next level is and what you need to get there. That is why competitive gamers and math winners are often highly successful at other things in life.
For fields that do not have a clear ladder one must climb, people struggle to understanding how they can meaningfully level up in their craft.
School gives you the exact things to learn. Reading materials, lectures and videos, projects to tackle. Same with corporate. Most people can climb high on the corporate ladder without ever coming up with a problem that they assign themselves.
People who think of “self learning” will picture someone reading a book in their spare time. In truth, consuming books is the laziest form of self learning you can possibly do.
The far more efficient way of learning is picking a project that is outside of your comfort zone. Be a bit delusional. Go into it with the expectations that you can do it. Oftentimes you will be surprised by the fact that you are, in fact, able to do it. Worst case scenario, you fail and learn.
Be open to failures. Elon was mocked for thinking he can go into rocket science. Mr Beast’s early YouTube videos are cringe as fuck (no offense). Is the upside on tackling this project worth more than the potential aura loss and time wasted?
General vs Specific learning.
For any field, understand what you NEED. Pareto Principle, 20% will net you 80%. Go read a book for this, watch a few YouTube videos, buy a course or two. Talk with AI for a bit.
“What is everything I need to know to have a solid foundational knowledge of __?”
Once you have this down, go straight into projects. Every roadblock, learn just enough to get you past that specific roadblock.
AI is here to stay. If you find yourself memorizing highly specific domain knowledge, chances are you are wasting your time. Knowing what NOT to learn is just as important as knowing what to learn, do not waste your time learning or doing a task a machine can do for you.
Befriend some cracked people in the field whom you genuinely admire and have respect for. Learn from them, offer them legitimate value back. It is absolutely insane the quality of knowledge you can get from someone already at the top of a field. My mentors have helped me cut down years if not decades that I would have otherwise wasted on my own experimentations.
Do not confuse the accumulation of knowledge or total time spent in a field with expertise. The only true measure of expertise is the difficulty of problems you are able to solve, and the quality of projects you are able to execute on.
Go follow some people on X, this is an amazing platform where insanely cracked people give away their sauce for free.
10% GDP growth, 10% unemployment.
I think we're going have to depend on most tech companies for UBI and eventually UHI. more investment in tech for the govt too! how else do we take care of society?