Jacopo Minniti

Undergraduate Student // AI Researcher

$ affiliations --current

Minerva University XLab (UChicago)

$ contact --email

jacopo.minniti004 [dot] gmail [dot] com

news_feed.log

>[2025-08-15]Talk at University of Chicago: 'The (not so) bitter lesson'

I had the opportunity to give a talk on the future of AI scaling, inductive biases, and a bit of history of the opposing paradigms in the field, all while trying to give a perspective on what the bitter lesson really says. Find the lecture here: https://uchicago.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=e86d18bd-5645-4e7e-94af-b33a011692b6

research_interests.py

neuro_ai.py

class NeuroAI(nn.Module):
    def __init__(self):
        super().__init__()
        self.synapses = DynamicSynapses()
        self.plasticity = HebbianLearning()
    
    def forward(self, x):
        # Biologically plausible forward pass
        return self.plasticity(self.synapses(x))

math_foundations.py

def prove_generalization(network):
    # Deriving bounds on sample complexity
    bound = vcdim(network) + log(1/delta)
    stability = spectral_norm(network.weights)
    
    # Toward a theory of intelligence
    return verify_convergence(bound, stability)

mech_interp.py

def analyze_representations(model):
    """Decoding internal states"""
    activations = run_with_hooks(model)
    circuits = identify_circuits(activations)
    return interpret_features(circuits)

reasoning_training.py

optimizer = torch.optim.AdamW(agent.parameters())
for step in range(max_steps):
    # Train strictly for long-horizon planning
    thought_chain = agent.think(problem)
    action = agent.decide(thought_chain)
    
    reward = env.step(action)
    loss = -log_prob(action) * reward
    loss.backward()

''' RESEARCH INTERESTS & PHILOSOPHY I am exploring the convergence of biological intelligence and artificial systems. My primary focus is on: 1. NeuroAI: Implementing biological constraints (plasticity, sparsity) to create more robust and efficient learning systems. 2. Mathematical Foundations: Developing a rigorous mathematical theory of intelligence to understand generalization and stability. 3. Mechanistic Interpretability: Reverse-engineering model weights to understand how high-level reasoning emerges from low-level circuits. 4. Agentic Reasoning: Training models to think, plan, and verify their own chain of thought over long time horizons. I believe true intelligence requires both structure (neuro-inspired architectures) and rigorous understanding (interpretability). '''

$ ls -a active_stack

PyTorchJAXvLLMtransformer-lensgymnasium

nice_quotes.txt

"The limits of my language mean the limits of my world."

– Wittgenstein

"Start where you are. Use what you have. Do what you can."

– Arthur Ashe

"To those human beings who are of any concern to me I wish suffering, desolation, sickness, ill-treatment, indignities—I wish that they should not remain unfamiliar with profound self-contempt, the torture of self-mistrust, the wretchedness of the vanquished: I have no pity for them, because I wish them the only thing that can prove today whether one is worth anything or not—that one endures."

– Nietzsche

"May you live every day of your life."

– Jonathan Swift

gallery_viewer.exe

How can such a damned place like Calabria be so beatiful?

1 / 4