https://hackerpaper.kaipfister.de/p/2510.24941/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=49298531urn:hackerpapers:mention:2510.24941:49298531Fri, 14 Aug 2026 13:39:02 GMT<p>Yeah, basically everything that becomes context in a session will bias perception and communication style -- subagents, plan lingo, prompt lingo, etc. And then if you write a plan with the comms context having been biased, the lingo will creep into the plan, and from the plan into the code and code comments. And from there, bad lingo will go on multiplying like rabbits... I usually think of it in terms of having a &quot;good&quot; or &quot;bad&quot; session. In a bad session, there is a harmful bias that you can only get rid of through a new session. For example, if you exposed too much context about, say, a…</p><p><a href="https://hackerpaper.kaipfister.de/p/2510.24941/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.LG