ODSC AI East 2026
2026-04-28..2026-04-30
-- online --
as the organisers put it
Join ODSC AI East 2027 in Boston with 3500+ AI and data science professionals. Learn from experts in LLMs, machine learning, and generative AI.
who it's for
agent developers, platform engineers, machine learning engineers, mlops engineers, ai safety engineers, data scientists
topics
production multi-agent architecture; agent sandboxing and governance; tool search and code mode; agent orchestration and runtimes; tensor-based logical reasoning; counterfactual Bayesian analysis; formal verification for generated code; embeddings with structure backpropagation; agent marketplaces and registries; practical clustering techniques
| title | author | length |
|---|---|---|
| Your MCP Server is Bad (and You Should Feel Bad) | Jeremiah Lowin | 27m |
FastMCP reports 8 million downloads and argues that wrapping a REST API often fails because agents have no persistent discovery and pay expensive iteration… | ||
| Agents for the Inner Loop and Outer Loop | Robert Brennan | 26m |
Platform runs cloud agents (started March 2024) that handle both inner-loop editing and outer-loop automation: agents open PRs to fix failing CI and merge… | ||
| DLGI: Before Things Go Too Far | David Campbell | 32m |
Argues for Domain-Limited General Intelligence as a practical alternative to chasing AGI, backed by a DEF CON 31 red‑teaming platform with 3,000 participants… | ||
| Tensor Logic: The Language of AI | Pedro Domingos, PhD | 30m |
Proposes TensorLogic, a language where relations map to Boolean tensors and rules map to Einstein summation plus a step nonlinearity, so logical joins become… | ||
| How to Build and Govern Production-Grade Multi-Agent Systems | Ali Arsanjani | 26m |
Production-grade multi-agent systems require concrete architecture and governance: use sandboxing (Docker, zero host access), an agent-to-agent… | ||
| Open Challenges for Programming Agents | Armando Solar-Lezama | 30m |
Claims that current coding agents hit an analysis bottleneck — they produce lots of code but miss systematic reasoning — and shows concrete tooling that uses… | ||
| How Machine Learning Can Help | Michael Littman, PhD | 26m |
Covers four concrete ways to teach computers: explicit programs, supervised examples, reinforcement learning, and inferring intent; presents experiments and… | ||
| AI Agents Unchained | Sinan Ozdemir | 30m |
A runbook of concrete wins and failures: a 2018 Chrome‑extension system (patented as the AI Communications Agent) actually automates phone lookups and payment… | ||
| Why LLMs Still Fail: Reasoning, Robustness, and Safety | Nouha Dziri | 25m |
Claims that state-of-the-art LLMs solve Olympiad math yet miss trivial tasks — e.g. GPT‑5 still fails 10x10 multiplication without tools as of Dec 2025 — and… | ||
| NANDA for Agentic Commerce: when agents roam on the Internet | Ramesh Raskar, PhD | 26m |
Describes a concrete architecture called NANDA that targets a marketplace where millions to trillions of AI agents discover, bid, negotiate and compose… | ||
| From Vibe Coding to Vericoding | Max Tegmark | 34m |
Argues for replacing trial‑and‑error coding with AI that writes code plus machine‑checked proofs, reporting a 12,000‑program benchmark and success rates… | ||
| Crushed by the AI Elephant | Rehgan Bleile | 27m |
Enterprise AI stalls because teams see only parts of the system and miss 43 people involved and nine to twelve month delays when pieces collide. The claim… | ||
| Counterfactual Analysis with Bayesian Models | Allen Downey, PhD | 31m |
Uses PyMC to fit hierarchical Bayesian regressions to Global Burden of Disease and World in Data mortality rates and runs posterior simulations to answer… | ||
| Embodied AI: A Cognitive Shift, Not a Cosmetic Change | Mohammad Soltaniehha, PhD | 36m |
Argues that giving AI voice or a face flips a cognitive switch that changes user behavior and trust, not just appearance, and demonstrates three working apps… | ||
| From Intelligence to Autonomy - Building the Infrastructure for the AI Workforce | Lake Dai | 32m |
AI shifts from copilots to autonomous collaborators and demands whole new infrastructure for data, reasoning, orchestration and trust. Key specifics: 95% of AI… | ||
| The Art of Clustering: The Good, The Bad and The Beautiful | Seth Levine | 25m |
Clustering workflow uses sentence-transformer embeddings, UMAP for dimensionality reduction, HDBSCAN for clustering and datamapplot/ Bokeh for interactive… | ||
| nothing matches | ||