Blog · Tag
hallucination.
4 posts in this archive.
Hallucination rate: a year-in measurement update
How we measure hallucination rate on grounded drafts, what the number looks like a year in, what moved it since the early baseline, and where the number lives in production for customers to see.
A full-year retrospective on shipping grounded AI
Twelve months of evidence on the grounded-AI thesis. The Stanford hallucination number measured against our corpus, four failure modes and which ones we closed, what changed under the hood, and what I would tell Q1 Bo.
Detecting ungrounded spans in drafts, line by line
A per-sentence classifier that flags which spans in a drafted RFP answer lack source coverage in the retrieved context. What it costs, what it catches, and what it still misses.
The hallucination budget, per claim
Treat hallucination as a cost: each claim in a draft has a probability of being mis-attributed. Here's how we budget it, how we trade latency against grounding strength, and why the budget is per-claim, not per-draft.
See the proposal workflow
Take the 5-minute tour, then start a trial workspace when you're ready to run a real pursuit against your own source material.