2026-11-01T00:27:34Z https://nostr.now Jodie Burchell 🇦🇺🇩🇪 https://nostr.now/npub1rv2wgr38nh2d7rsx6l75rrsmh60z6me3jru9kksnerd5zzrttr3qflnamt https://cdn.fosstodon.org/accounts/avatars/109/314/100/180/709/017/original/94ca6dde2cdfa495.png https://cdn.fosstodon.org/accounts/avatars/109/314/100/180/709/017/original/94ca6dde2cdfa495.png https://nostr.now/nevent1qqsxl3snty3u2l3hccg5y5dactdqcrd07endu2a0vpw3fzur0elha2czyqd3feqwy7wafhcwqmtl6svwrwlfutt0xxg0sk66z0ydksggddvwy5upc66 Have you ever looked at the impressive results that LLMs get on benchmarks or difficult exams and wondered if these results are everything they seem? Some of these are due to something called data leakage, where assessments leak into the training data and the models memorise the answers.<br/><br/>If you&#39;d like to learn more about how this classic pitfall of machine learning calls many of the results we see on LLM performance into question, check out my latest blog post.<br/><br/><a href="https://t-redactyl.io/posts/2025-12-30-data-leakage-llm-measurement/">https://t-redactyl.io/posts/2025-12-30-data-leakage-llm-measurement/</a> 2026-01-13T15:30:03Z https://nostr.now/nevent1qqsdtumy9efkkpvcllsv8ra3ts3f0dt7cctxzeyqhjah0j4ca6k57wgzyqd3feqwy7wafhcwqmtl6svwrwlfutt0xxg0sk66z0ydksggddvwyzdlch0 The call for proposals for <span itemprop="mentions" itemscope itemtype="https://schema.org/Person"><a itemprop="url" href="/npub1rwpqmzka6h6shpag8x6d6m0dksu7athev4yaqusug00vncp9lrcqldpsqf" class="bg-lavender dark:prose:text-neutral-50 dark:text-neutral-50 dark:bg-garnet px-1"><span>EuroPython</span> (<span class="italic">npub1rwp…psqf</span>)</a></span> is now open, and we&#39;d love to get all of your submissions! You&#39;ve got until January 27th to send us all of your insightful, inspiring and outlandish ideas about Python and its community ❤️🐍<br/><br/><a href="https://www.youtube.com/watch?v=YYbqXEb2b7c">https://www.youtube.com/watch?v=YYbqXEb2b7c</a> 2025-01-16T09:59:17Z