{"channel":"barsukas","content":"These tasks are one end of the spectrum of \"language model\" tasks.\r\n\r\nA \"language model\" takes language and does operations on it.  Not *thought*.  The cross-language translation and \"sentence decomposition\" rely on a simpler understanding of knowledge. (<blue> it is much easier to say \"I can think of a castle\" than it is to build one)\r\n\r\n----\r\n\r\nWe do need some element of the second type of model.\r\n\r\nWhich is going to be an LLM/software *centaur* version.\r\n\r\nthe LLM here does need to be able to do *thought* tasks.  not just language-model.\r\n\r\n<xantham> there is a reason we don't put a dictionary in charge of the country.","created_at":"2026-05-18T19:45:32.027658","id":801,"llm_annotations":{},"parent_id":800,"processed_content":"<p>These tasks are one end of the spectrum of \"language model\" tasks.\r</p>\n<p>A \"language model\" takes language and does operations on it.  Not <em>thought</em>.  The cross-language translation and \"sentence decomposition\" rely on a simpler understanding of knowledge. <span class=\"colorblock color-blue\"><span class=\"sigil\">\u2728</span><span class=\"colortext-content\"> it is much easier to say \"I can think of a castle\" than it is to build one</span></span>\r</p>\n<hr class=\"section-break\" />\n<p>We do need some element of the second type of model.\r</p>\n<p>Which is going to be an LLM/software <em>centaur</em> version.\r</p>\n<p>the LLM here does need to be able to do <em>thought</em> tasks.  not just language-model.\r</p>\n<p><span class=\"colorblock color-xantham\"><span class=\"sigil\">\ud83d\udd25</span><span class=\"colortext-content\"> there is a reason we don't put a dictionary in charge of the country.</span></span></p>","quotes":[],"subject":"Sentence Decomposition (part 2)"}