The financial desks we read, gathered in one place. Stories we are licensed to carry are reproduced in full with the writer credited; everything else is a headline and a short quotation that links straight to the publisher.
Towards Data Science AI Full text
Re-reading my own IBM patent on real-time concert feedback as what it actually was: an agentic loop with multimodal perception, memory-grounded inference, and a human in the loop. What it got right, and what a decade of hindsight teaches…
Towards Data Science AI Full text
Three vision AI models ignored the pretty image, yet GPT-4o invented answers and Claude kept answering B.
Towards Data Science AI Full text
Is this the JEV killer?
Towards Data Science AI Full text
Beyond basic ReAct loops: six production-oriented architectures for building autonomous, reliable, and scalable LLM agents.
Towards Data Science AI Full text
Add architectural guardrails around how agents read untrusted sources and use them in the workflow.
Towards Data Science AI Full text
A one-line formula for how often an LLM's top token flips, and why identical completions fall apart after about a hundred tokens
Towards Data Science AI Full text
How a decision-first model can catch risky tool calls before they turn into real-world actions
Towards Data Science AI Full text
The cost of control
Towards Data Science AI Full text
Part 1: Understanding the technologies shaping our future
Towards Data Science AI Full text
Autoregressive rollout and uncertainty propagation. Second in a series on probabilistic forecasting for physical signals.
Towards Data Science AI Full text
RAG retrieves. Agents act. I built both separately, connected them explicitly, and ran the same nine tasks through all three systems.
Towards Data Science AI Full text
I tested TypeSafe AI’s Jev on 3,080 classification tasks to see how its accuracy, latency, calibration, and confidence compare with LLMs — and whether it works as a practical decision layer for AI systems.
Towards Data Science AI Full text
Get more out of your coding agent subscriptions
Towards Data Science AI Full text
Retrieval is not evidence. How to build AI that proves its own claims.
Towards Data Science AI Full text
Why a green test suite can mean nothing
Towards Data Science AI Full text
The reliability mechanisms we add to LLM pipelines are often the ones that make them confidently wrong.
End of the wire
Stories marked Full text are reproduced here under the terms their publisher allows, with the writer credited and the original linked. Everything else is a headline and a short quotation that links straight to the publisher. How we quote · Our sources
