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 agent builders today.
Three vision AI models ignored the pretty image, yet GPT-4o invented answers and Claude kept answering B.
Beyond basic ReAct loops: six production-oriented architectures for building autonomous, reliable, and scalable LLM agents.
Add architectural guardrails around how agents read untrusted sources and use them in the workflow.
A one-line formula for how often an LLM's top token flips, and why identical completions fall apart after about a hundred tokens
How a decision-first model can catch risky tool calls before they turn into real-world actions
AI agents can now write more code than any of us can read. That changed how I think about AI.
Three moves to decode the hype
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 agent builders today.
Three vision AI models ignored the pretty image, yet GPT-4o invented answers and Claude kept answering B.
AI agents can now write more code than any of us can read. That changed how I think about AI.
Three moves to decode the hype
AI agents can now write CUDA kernels that outperform PyTorch—but proving those speedups are real is the harder problem. I put them to the test on an NVIDIA DGX Spark and found that benchmark design matters just as much as the code.
A diffusion head for probabilistic time series forecasting: why a forecast can get the mean and the variance right and still describe a future that never happens, and how to fix it.
Sorting through the good, bad, and ambiguous aspects of vibe coding
Don't miss our most-read and -shared stories of the past month
Beyond basic ReAct loops: six production-oriented architectures for building autonomous, reliable, and scalable LLM agents.
How statistical moments connect the mean, the variance, and higher powers of a distribution
First in a series on probabilistic forecasting for physical signals. Next: what happens when you roll the forecast forward more than one step.
When Codex is the right shape for the problem, when Claude Code is, and how I split 5 specialist agents between them on dense AI capacity work.
Why the skill-inflation panic is aimed at the wrong thing, and what it costs to make agent knowledge a build artifact instead of a file.
A real Weave project that regression-tests three OpenAI models against the exact reply format your app depends on.
