{"channel":"cities","content":"the new \"lexer\"-based parser has crossed the hump of possibility.\r\n\r\nit took roughly 2 days of effort (plus 3 days of complaining, earlier).  this is, arguably, slower than it would have been for me to write this *without* using the *machine*.\r\n\r\nthere are a few minor things to fix before it replaces the new system.  those are in the next list.\r\n\r\n----\r\n\r\ntoday's things:\r\n# New lexer bugfixes - lists format incorrectly, PGN templates don't work, quotes aren't stored\r\n# Fix the test framework - occasionally it deletes the (local) prod database\r\n# Better export/import tools - should be able to load the prod database locally by transferring a JSON file\r\n# *Don't* try to add << i-Ching >> based features\r\n# Try to get the << LLM Magic Query >> working - based on a short prompt (\"Tell me about George Washington\", \"What does baking powder do\"), figure out the best extended prompt, and then get the response.","created_at":"2025-01-23T15:34:38.768053","id":145,"llm_annotations":{},"parent_id":140,"processed_content":"<p>the new \"lexer\"-based parser has crossed the hump of possibility.\r</p>\n<p>it took roughly 2 days of effort (plus 3 days of complaining, earlier).  this is, arguably, slower than it would have been for me to write this <em>without</em> using the <em>machine</em>.\r</p>\n<p>there are a few minor things to fix before it replaces the new system.  those are in the next list.\r</p><hr class=\"section-break\" /><p>today's things:\r</p>\n<ul>\n<li class=\"number-list\"> New lexer bugfixes - lists format incorrectly, PGN templates don't work, quotes aren't stored\r</li>\n<li class=\"number-list\"> Fix the test framework - occasionally it deletes the (local) prod database\r</li>\n<li class=\"number-list\"> Better export/import tools - should be able to load the prod database locally by transferring a JSON file\r</li>\n<li class=\"number-list\"> <em>Don't</em> try to add <span class=\"literal-text\">i-Ching</span> based features\r</li>\n<li class=\"number-list\"> Try to get the <span class=\"literal-text\">LLM Magic Query</span> working - based on a short prompt (\"Tell me about George Washington\", \"What does baking powder do\"), figure out the best extended prompt, and then get the response.</li>\n</ul>","quotes":[],"subject":"great falls (4/5)"}