Taken out of context: On measuring situational awareness in LLMs · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2309.00667/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTTaken out of context: On measuring situational awareness in LLMs — mentioned by famouswaffleshttps://news.ycombinator.com/item?id=42674556urn:hackerpapers:mention:2309.00667:42674556Sun, 12 Jan 2025 16:12:17 GMT<p>&gt;LLMs do not have such kind of meta-knowledge over their training data or weights. Not sure this is a claim that can be confidently made. https://arxiv.org/abs/2309.00667 https://x.com/flowersslop/status/1873115669568311727?t=eBMbK...</p><p><a href="https://hackerpaper.kaipfister.de/p/2309.00667/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CLTaken out of context: On measuring situational awareness in LLMs — HN submissionhttps://news.ycombinator.com/item?id=38183101urn:hackerpapers:submission:2309.00667:38183101Tue, 07 Nov 2023 21:28:41 GMT<p>Taken out of context: On measuring situational awareness in LLMs</p><p></p><p>2 points; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2309.00667/">Paper and source history</a>. A submission is not an endorsement.</p>cs.CL