Gábor SEBESTYÉN 🇭🇺🇪🇺🇺🇦<p>An interesting take on make AI teach themselves without human interaction. Absolute Zero: Reinforced Self-play Reasoning with Zero Data <a href="https://andrewzh112.github.io/absolute-zero-reasoner/" rel="nofollow noopener noreferrer" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">andrewzh112.github.io/absolute</span><span class="invisible">-zero-reasoner/</span></a> <a href="https://czinege.social/tags/ml" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ml</span></a> <a href="https://czinege.social/tags/ai" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>ai</span></a> <a href="https://czinege.social/tags/zerodata" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>zerodata</span></a> <a href="https://czinege.social/tags/research" class="mention hashtag" rel="nofollow noopener noreferrer" target="_blank">#<span>research</span></a></p>