Mastokarl 🇺🇦<p>Watching the top LLMs battle it out by playing chess in Kaggle is quite an experience.</p><p>Like DeepSeek musing over tactical considerations and structural advantages while it’s queen hangs for 5 moves with no AI noticing it. </p><p>But sometimes it really feels like thinking chess players (impressed by a mating attack by o4-mini). Sometimes. Not often.</p><p><a href="https://youtu.be/Kd2SszjZwr0?si=lSEU1AGs7xw8JCHa" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">youtu.be/Kd2SszjZwr0?si=lSEU1A</span><span class="invisible">Gs7xw8JCHa</span></a></p><p><a href="https://mastodon.social/tags/kaggle" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>kaggle</span></a> <a href="https://mastodon.social/tags/deepmind" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>deepmind</span></a> <a href="https://mastodon.social/tags/llm" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>llm</span></a> <a href="https://mastodon.social/tags/benchmark" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>benchmark</span></a></p>