Aleten editorial
News and research
AI research coverage and Ackren development updates, with sources and limits alongside the claims.
Archive dates follow the research, development record or newsletter edition. This collection was first published on 25 September 2026.
Evidence, explanations and what changed at Ackren
A September research digest: an inspectable teaching example, the limits of replay, and recent work on testing AI explanations.
Read article →Teaching a conversational engine, with the evidence visible
A recorded local example shows Ackren deriving an answer from a statement and a rule. The prototype remains bounded and has not completed release qualification.
Read article →Repeatable is not the same as correct
Ackren’s recorded evaluation separates repeatable execution from correct interpretation. That distinction matters when assessing an AI explanation.
Read article →To test an AI explanation, change the evidence it cites
A September preprint tests visual explanations through controlled image changes. The wider lesson is to test explanations against evidence, with clear limits on what a passing test proves.
Read article →Verification starts before the solver
Research on language-to-planning systems highlights a difficult boundary: a formally checked result depends on what the system translated from the user’s request.
Read article →Follow via RSS · Newsletter archive. This is a web publication; no email subscription is required.