Salvatore Raieli

Member-only story |LLM|CREATIVITY|AI|HALLUCINATION| Exploring the Role of Hallucinations, Dependencies, and Imagination in AI Creativity Salvatore Raieli · Follow Published in Towards Data Science · 11 min read · 4 hours ago — Image generated by the author using DALL-E Creativity requires the courage to let go of certainties. — Erich Fromm Creativity involves breaking out of established patterns in order to look at things in a different way. — Edward de Bono Creativity is considered

|ARTIFICIAL INTELLIGENCE|MEMORY|NEURAL NETWORK|LEARNING| Memory can play tricks; to learn best it is not always good to memorize Salvatore Raieli · Follow Published in Towards Data Science · 12 min read · 2 hours ago — image generated by the author using DALL-E No man has a good enough memory to be a successful liar. — Abraham Lincoln Memory is more indelible than ink. — Anita Loos Memorize bad, generalization good. This is considered as a

|LLM|TRANSFORMER|FOUNDATION MODEL|GRAPH|NETWORK| Disconnected from the other modalities graphs wait for their AI revolution: is it coming? Salvatore Raieli · Follow Published in Towards Data Science · 11 min read · 12 hours ago — Image created by the author using DALL-E “If the foundation is solid, everything else will follow.” – Unknown “The loftier the building, the deeper must the foundation be laid.” – Thomas à Kempis Foundation models have changed artificial intelligence in recent

|LLM|INTERPRETABILITY|SPARSE AUTOENCODERS|XAI| A deep dive into LLM visualization and interpretation using sparse autoencoders Salvatore Raieli · Follow Published in Towards Data Science · 13 min read · 11 hours ago — Image created by the author using DALL-E All things are subject to interpretation whichever interpretation prevails at a given time is a function of power and not truth. — Friedrich Nietzsche As AI systems grow in scale, it is increasingly difficult and pressing to

|LLM|INTELLIGENCE|REASONING| Exploring the limits of artificial intelligence: why mastering patterns may not equal genuine reasoning Salvatore Raieli · Follow Published in Towards Data Science · 13 min read · 9 hours ago — image generated by the author using DALL-E I have hardly ever known a mathematician who was capable of reasoning. — Plato Reasoning draws a conclusion, but does not make the conclusion certain, unless the mind discovers it by the path of experience.

|LLM|AI|HUMAN MIND|MEMORY|COGNITION| Exploring the Eerie Parallels and Profound Differences Between AI and Human Memory Salvatore Raieli · Follow Published in Towards Data Science · 10 min read · 3 hours ago — image by the author using AI The limits of my language are the limits of my mind. — Ludwig Wittgenstein The true art of memory is the art of attention. — Samuel Johnson Language is one of the most important capabilities of human

|AI|CONTINUAL LEARNING|DEEP LEARNING LIMITS| Understanding the limits of deep learning and the quest for true continual adaptation Salvatore Raieli · Follow Published in Towards Data Science · 14 min read · 2 hours ago — image by the author using AI “The wise adapt themselves to circumstances, as water moulds itself to the pitcher.” — Chinese Proverb “Adapt or perish, now as ever, is nature’s inexorable imperative.” — H. G. Wells Artificial intelligence in recent

|LLM|PROMPT ENGINEERING|COT|REASONING| Sometimes few words are enough: reducing output length for increasing accuracy Salvatore Raieli · Follow Published in Towards Data Science · 9 min read · 9 hours ago — image created by the author using AI Brevity is a great charm of eloquence. — Marcus Tullius Cicero Brevity and conciseness are the parents of correction. — Hosea Ballou Large language models (LLMs) have shown interesting capabilities in the field of reasoning. With their

|LLM|HALLUCINATION| MEMORY| Exploring How Memory Mechanisms Can Mitigate Hallucinations in Large Language Models Salvatore Raieli · Follow Published in Towards Data Science · 7 min read · 12 hours ago — image created by the author using AI A hallucination is a fact, not an error; what is erroneous is a judgment based upon it. — Bertrand Russell Large language models (LLMs) have shown remarkable performance, but are still plagued by hallucinations. Especially for sensitive

|LLM|AI|GENETIC| Exploring phylogenetic algorithms to predict the future of large language models Salvatore Raieli · Follow Published in Towards Data Science · 9 min read · 8 hours ago — image by the author using AI I’m fascinated by the idea that genetics is digital. A gene is a long sequence of coded letters, like computer information. Modern biology is becoming very much a branch of information technology. — Richard Dawkins There are plenty of