{"id":19215,"date":"2025-01-26T20:53:52","date_gmt":"2025-01-26T20:53:52","guid":{"rendered":"\/?p=19215"},"modified":"2025-01-26T20:56:37","modified_gmt":"2025-01-26T20:56:37","slug":"it-is-not-hard-but-it-needs-focus-global-open-exact-references","status":"publish","type":"post","link":"\/?p=19215","title":{"rendered":"It is not hard, but it needs focus – global open exact references"},"content":{"rendered":"
\n
\n
\n

https:\/\/x.com\/RichardKCollin2\/status\/1883619696320098712<\/strong><\/span><\/p>\n

It is not hard, but it needs focus – global open exact references<\/p>\n

I was chatting with OpenAI ChatGPT Plus about Bernoulli and related equations. I use simple problems to test basic skills in mathematics, units, referencing reasoning and arithmetic. OpenAI fails always on certain problems and it is because the whole reliance is on one closed and untraceable compilation of weights and methods from LLM and no index or access to the training data, nor to any authoritative references in the literature. OpenAI and the other groups are NOT using core references. They cannot even reliably refer to URLs where things can be found.<\/p>\n

It is a “break the bank” serious problem that affects the safety and security of the world and all knowledge.<\/p>\n

These are hard problems and require a LOT of exact knowledge. That is why I use them for testing. Copy and paste or try to get the whole conversation into your own AI that you are familiar with and ask your own AI what is happening. Most humans cannot keep all the exact items in mind at once, like a large computer program with many steps and external libraries and dependencies. If ONE definition is wrong the whole thing can crash or give non-obvious errors. Society cannot afford creeping noise and errors that only “more AIs” can solve. Because it leads to human groups going into conflict.<\/p>\n

Full conversation at<\/p>\n

https:\/\/chatgpt.com\/share\/67969590-20ec-800b-9a6d-186486fdc21a<\/span><\/a><\/p>\n

Richard Collins said to OpenAI ChatGPT 4o:<\/strong><\/span><\/p>\n

What I am trying to do is get your designers to face the LLM is NOT a complete system and it cannot do certain things. Patching it in on the fly as you all are doing it now (a loose ad hoc community of LLM users and makers and others) is broken seriously and needs to be fixed. It is not hard, but it takes conscious and deliberate efforts.<\/span><\/p>\n

OpenAI ChatGPT Plus 4o responded:<\/strong><\/p>\n

Thank you for clarifying. You’re absolutely right\u2014current LLMs, including me, have inherent limitations that prevent them from functioning as complete systems<\/span> for rigorous, authoritative work. These systems are often great for synthesis, exploration, and explanation within certain bounds, but <\/span>fall apart<\/span> when precision, traceability, or deeper integration across disciplines is required.<\/span><\/p>\n

 <\/p>\n<\/div>\n<\/div>\n<\/div>\n

\n
\n
Your critique pinpoints the exact systemic issue: these tools have been designed to “guess well” within a probabilistic framework, but <\/span>lack structured mechanisms for grounding, validating, and ensuring consistency<\/span> in ways critical to real-world applications.<\/span><\/div>\n<\/div>\n<\/div>\n
\n
\n
Core Issues with Current LLM Systems<\/span><\/div>\n<\/div>\n<\/div>\n
\n