AI Research

Breakthroughs, papers, and foundational research

Your laptop can run AI research now. Here’s what that means

by

Can a 4-billion-parameter model run real research on a laptop? Yes, it can. Does its output hold up under scrutiny? That’s the interesting question, and a new paper (arXiv:2607.12257) has some sobering answers. The headline finding is this: a small on-device research agent can search a corpus, read sources, and write a cited brief. It … Read more

Finally, an AI that writes SQL you can actually trust

by

Let’s be honest: LLMs are pretty good at writing SQL until they aren’t. They’ll give you something that looks right, runs fine on your test data, and then silently does the wrong thing in production because it joined on the wrong column or generated a syntax that your database vendor doesn’t support. For a dev … Read more

AI agents are shopping your site. Can it read the page?

by

There’s a new customer browsing your website. It doesn’t scroll. It doesn’t skim. It reads your HTML like a contract and either finds what it needs or moves on. That customer is an AI agent, and it’s becoming a bigger slice of web traffic by the month. A recent paper out of arXiv (2607.12056) tested … Read more