Ask Me Anything: A simple strategy for prompting language models · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2210.02441/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTAsk Me Anything: A simple strategy for prompting language models — mentioned by james-revisoaihttps://news.ycombinator.com/item?id=35671631urn:hackerpapers:mention:2210.02441:35671631Sat, 22 Apr 2023 22:52:10 GMT<p>Prompt engineering made more sense before RLHF/instruct models. Back then text just continued onwards, and many papers found ridiculous gains on conforming with intended output (and therefore properties of output) by finding a suitable widespread online format. Example: I think all Question/Answer forums, and places like StackOverflow, used a certain format like &#x27;Q:&#x27; - that worked much better for question content with high quality answers. One paper, &quot;Ask me anything&quot; showed that formulating tasks as questions-answers resulted in much more effective prompts: https://arxiv.org/abs/2210.02441…</p><p><a href="https://hackerpaper.kaipfister.de/p/2210.02441/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CL