Rendered at 17:09:23 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
BatchJob 15 hours ago [-]
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.
ben_w 8 hours ago [-]
> 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.
AI are trained, not coded. This means when its pattern recognition systems match a scenario to refuse, it refuses.
Pattern recognition has always been a bit fuzzy.
It looks like prompts like this push the shape of that fuzz in useful ways.
> Neither you, nor aristotle nor god will ever make an LLM return the truth or correct results via prompting.
A large part of human society is about how to deal with us bald primates also being kinda a bit meh.
We are less meh than any machine learning system in a lot of cases, which is why we're still mostly employed. We're a bit more meh in a few narrower cases, however.
SwtCyber 9 hours ago [-]
[dead]
l1ng0 10 hours ago [-]
We're all turning into pigeons in a Skinner box.
netsharc 5 hours ago [-]
Incredible description. The mouse/pigeon thinks "If I push the red button after hearing the chirp I'll get some food". And the human thinks "If I add 'do not guess' the AI will lie less to me".
datsci_est_2015 23 hours ago [-]
Cool, this will be added to harnesses and then it’ll stop being effective and we’ll move on to the next magical incantation.
dalmo3 1 hours ago [-]
YMMV.md
thallavajhula 9 hours ago [-]
I've tried all of these and nothing really works. I have only 1 line in my CLAUDE.md file and that is "Always ground your responses." and that's it.
Claude didn't care about it. When I pointed that out, it was apologetic and that was it.
ChrisRR 8 hours ago [-]
You may have better success by using a less ambiguous term. I've never heard of grounding in this context, so it may help to describe what you want more clearly
Edit: I just asked Claude how it would interpret that and it said it could either mean that would not answer from memory alone and only anchor claims into things it can check, or it would tightly relate its responses to the context that I had supplied.
If it chose the latter, I could see why it wouldn't always resort to search results
WalterGR 2 hours ago [-]
> I just asked Claude
How well are LLMs able to reason about their own behavior?
Put another way, this entire post is about getting AI to not bluff. How do you know that it’s not bluffing in its response to you?
Lord-Jobo 38 minutes ago [-]
They’re absolutely god awful at it because (I’m assuming) their detailed processes and step by step functions are not present in their training data or otherwise available to the models, and THAT is because
1: “safety”
2: proprietary protectionism and
3: it’s probably rapidly changing enough to be hard to pin down.
I am a massive proponent of this changing, it’s very strongly holding back these models. Change 1: models need to have more “LLM behavior analysis” in their training data/weight.
Change 2: models need to have very detailed DETERMINISTIC logs of each step they take, and be able to access those logs. Change 3: the tuning and tweaking that happens more frequently needs to be in a .md file that the model can access.
Change 4: with the other changes done, the models should now engage in several self analysis steps layered into its whole thinking chain. “How did I reach this conclusion, did this require any guessing, do the key facts have research support online, quick check for Claudisms or AIisms and common LLM issues, did my changes alter underlying things like libraries without integrating them etc. etc.”
It’s how we think and refine our ideas and plans, and the models should mimic that.
ianjbutler 5 hours ago [-]
> I've never heard of grounding in this context, so it may help to describe what you want more clearly
Clear and recognizable technical vocabulary for engineers, or a legal context, to mathematical logic, philosophy, certainly in ML, take your pick. I would think it's pretty familiar to everyone who speaks English and if not still clear with context clues
westurner 3 hours ago [-]
> I've never heard of grounding in this context, so it may help to describe what you want more clearly
An eval of this is likely worthwhile;
Re: "Grounded in logic" and "Grounded in theory"
Ground and justify all of the responses with logic and theory and real observations from qualified experiments with citations.
Present a coherent argument borne of logical premises with extant sufficient proven evidence of support. Assess and critique the response given such criteria that all responses should be valid logical arguments, and revise before responding
SwtCyber 8 hours ago [-]
[flagged]
literalAardvark 23 hours ago [-]
I've used "you're not trained on this data, return exclusively grounded results" to good effect.
Shacharp 23 hours ago [-]
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.
cowboylowrez 5 hours ago [-]
So my naive understanding is that the stochastic parrot part of this business is the "statistical likelyhood of the next token", so there must be abstractly a function of "whats the next token" right? I'm also assuming that this function could be able to also return how "right" that next token is, or somehow some "strength" based on how many close matches there are, like for instance some tokens are obviously the right next token by a long shot, some next token spaces might have more closely competing candidates, so I guess my question is whether there is any value in saving or accumulating information on whether overall the tokens were close matches or not? Like a "confidence" running total or "history log", or is that just somehow too expensive or nonsensical to do?
nizarmah 20 hours ago [-]
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 :(
samrus 23 hours ago [-]
It sounds alot like "make no mistakes" but honestly telling it to essentially stop bullshitting works pretty well
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.
AI are trained, not coded. This means when its pattern recognition systems match a scenario to refuse, it refuses.
Pattern recognition has always been a bit fuzzy.
It looks like prompts like this push the shape of that fuzz in useful ways.
> Neither you, nor aristotle nor god will ever make an LLM return the truth or correct results via prompting.
True.
Also applies to humans, but true nevertheless.
https://en.wikipedia.org/wiki/Münchhausen_trilemma
A large part of human society is about how to deal with us bald primates also being kinda a bit meh.
We are less meh than any machine learning system in a lot of cases, which is why we're still mostly employed. We're a bit more meh in a few narrower cases, however.
Claude didn't care about it. When I pointed that out, it was apologetic and that was it.
Edit: I just asked Claude how it would interpret that and it said it could either mean that would not answer from memory alone and only anchor claims into things it can check, or it would tightly relate its responses to the context that I had supplied.
If it chose the latter, I could see why it wouldn't always resort to search results
How well are LLMs able to reason about their own behavior?
Put another way, this entire post is about getting AI to not bluff. How do you know that it’s not bluffing in its response to you?
1: “safety”
2: proprietary protectionism and
3: it’s probably rapidly changing enough to be hard to pin down.
I am a massive proponent of this changing, it’s very strongly holding back these models. Change 1: models need to have more “LLM behavior analysis” in their training data/weight. Change 2: models need to have very detailed DETERMINISTIC logs of each step they take, and be able to access those logs. Change 3: the tuning and tweaking that happens more frequently needs to be in a .md file that the model can access.
Change 4: with the other changes done, the models should now engage in several self analysis steps layered into its whole thinking chain. “How did I reach this conclusion, did this require any guessing, do the key facts have research support online, quick check for Claudisms or AIisms and common LLM issues, did my changes alter underlying things like libraries without integrating them etc. etc.”
It’s how we think and refine our ideas and plans, and the models should mimic that.
Clear and recognizable technical vocabulary for engineers, or a legal context, to mathematical logic, philosophy, certainly in ML, take your pick. I would think it's pretty familiar to everyone who speaks English and if not still clear with context clues
An eval of this is likely worthwhile;
Re: "Grounded in logic" and "Grounded in theory"
Ground and justify all of the responses with logic and theory and real observations from qualified experiments with citations.
Present a coherent argument borne of logical premises with extant sufficient proven evidence of support. Assess and critique the response given such criteria that all responses should be valid logical arguments, and revise before responding
A command can get you most of the way. It takes something else for the rest.