The LLM will take a statistical path to reply and will not refuse to do so under any circumstances except where its been coded to do so.
Your examples are contrived and will not be borne out in any significant way. Inaccuracies are usually not simply made up claims they are false information based on statistical paths to misleading results or which elude the current context. LLMS dont understand the word dont. LLMS dont understand the meaning of any words.
Neither you, nor aristotle nor god will ever make an LLM return the truth or correct results via prompting.
The "do not guess" sentence works but the last 20% will only close when a system stops being told to avoid guessing and actually knows what it does not know.
A command can get you most of the way. It takes something else for the rest.
The LLM will take a statistical path to reply and will not refuse to do so under any circumstances except where its been coded to do so.
Your examples are contrived and will not be borne out in any significant way. Inaccuracies are usually not simply made up claims they are false information based on statistical paths to misleading results or which elude the current context. LLMS dont understand the word dont. LLMS dont understand the meaning of any words.
Neither you, nor aristotle nor god will ever make an LLM return the truth or correct results via prompting.
Cool, this will be added to harnesses and then it’ll stop being effective and we’ll move on to the next magical incantation.
I've used "you're not trained on this data, return exclusively grounded results" to good effect.
The "do not guess" sentence works but the last 20% will only close when a system stops being told to avoid guessing and actually knows what it does not know.
A command can get you most of the way. It takes something else for the rest.
It sounds alot like "make no mistakes" but honestly telling it to essentially stop bullshitting works pretty well
I mean if we can measure it, then we can probably have a way to validate it programmatically. I gave up on drawing restrictions using prompts :(
[flagged]
[dead]
[flagged]