A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2303.10420/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTA Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models — mentioned by syllogismhttps://news.ycombinator.com/item?id=37443921urn:hackerpapers:mention:2303.10420:37443921Sat, 09 Sep 2023 10:43:44 GMT<p>(Original author of spaCy and Explosion CTO here) Okay so, first some terminology. LLMs can mean a bunch of different things, people call models the size of BERT LLMs sometimes. So let&#x27;s talk specifically about in-context learning (ICL) with either zero or a few examples. So we&#x27;ll say LLM ICL, and contrast that with techniques where you annotate enough data to train with, which might only be something like 10-40 hours of annotation. The something you do with that data is probably training a task-specific classification model initialised with weights from a language modelling objective. This…</p><p><a href="https://hackerpaper.kaipfister.de/p/2303.10420/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CLA Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models — HN submissionhttps://news.ycombinator.com/item?id=35263649urn:hackerpapers:submission:2303.10420:35263649Wed, 22 Mar 2023 16:39:00 GMT<p>A comprehensive capacity analysis of GPT-3 and GPT-3.5 models</p><p></p><p>2 points; 0 discussion replies on HN. <a href="https://hackerpaper.kaipfister.de/p/2303.10420/">Paper and source history</a>. A submission is not an endorsement.</p>cs.CL