96% Correct Next Token Prediction, with No DNN, no Training, auto-distilled model
Over the last 12 months, I’ve built a model to predict the next token and to suggest synonyms or related queries to a user prompt, with 100% correct predictions on the training set in one shot, without training or deep neural networks (DNNs). The same model is now integrated in some of the most recent […]
Read More
Invitation to Crack Codes Using AI
Could you use AI to crack a cypher? For instance, predict the next bits in bitstreams produced by a high-quality PRNG (pseudo-random generator). Or correctly guessing the next bit in sub-sequences of 100,000 consecutive binary digits of π starting at arbitrary positions, with a success rate above 55%. Without knowing that the digits come from […]
Read More
NPG: New Random Generator, 3x Faster & Stronger than PCG64
The NumPy library in Python, and many other systems, relied on the Mersenne Twister PRNG (pseudo-random number generator) for a long time. It was slow and did not mimic randomness well enough, failing some statistical tests. In addition, it could be cracked, raising security issues. It was replaced recently by PCG64 which addresses some of […]
Read More
Mesmerizing Video that will Make you Love Math, Engineering, and Probability
Featuring the roots of various polynomials whose coefficients are the binary digits of numbers like π. Complex roots cluster around the circle, and the few real ones are on the horizontal X-axis (positive on the right, negative on the left). Download the free paper to see how to interpret the colors and get the […]
Read More
Podcast with Vincent Granville: Hallucination-Free AI Models
Fireside chat with Vincent Granville, CAIO & Co-Founder at BondingAI.io. Hosted by Benjamin Johnson, CEO & Co-Founder at Particle41. Dive into AI advancements with Vincent Granville, as he reveals breakthrough methods in hallucination-free AI models and synthetic data innovations. Join us in this episode of the Particle Accelerator Podcast as we welcome Vincent Granville, Co-Founder […]
Read More
Quantum, chaotic and fractal types of algorithmic convergence
For centuries, mathematicians worked on problems where the convergence is either smooth or does not happen. Now the concept of chaotic convergence is mainstream, popularized by the stochastic gradient descent in deep neural networks, central to LLMs. In my most recent book here, I discuss many cases involving various types of chaotic convergence. In some […]
Read More
How Random are the Digits of π? State of the Art & Free Book on the Topic
Over the last 10 years, I spent a lot of time analyzing the digits of the classic math constants such as π, e, log 2, √2 and so on. Not testing them for randomness but trying to formally prove that they are undistinguishable from random bit streams. And trying to identify which constants are the […]
Read More
Pi Day in the age of AI — The Missing $1m Millenium Prize
Pi Day is celebrated every year on 3/14. Enjoy and share the video I created with our “Pi Day AI agent” at BondingAI, generating hundreds of webpages, turning each one in a screenshot (a frame in the video). All done in Python with source code available here. The video is also on YouTube, here. For […]
Read More
xLLM Version 2.0: GitHub Repository with Innovative AI Agents
I am putting all the new code and documentation about xLLM v 2.0 on GitHub, starting with various AI agents. At least, what is open-source and public (there is a lot more behind the public material). All home-made from scratch with radically different technology. You can check the new repository, here. Start with the README […]
Read More
Checking for Randomness: Replacing Test Batteries with a Single Test
In cybersecurity applications where replicability is critical, or when building pseudo-random number generators, it is typical to perform a large number of various tests to check if a sequence of bits is random enough for practical purposes. This is also true in scientific research, to assess whether or not the digits of π or other […]
Read More
You must be logged in to post a comment.