Was actually pulling on a similar thread as I saw announcement so I integrated it just for fun. Have been only running this on my Framework Desktop but should be runnable elsewhere
https://github.com/olafura/gemma-4-mic-transcribe
Show HN: Cactus Hybrid: We taught Gemma 4 to know when it's wrong
11–20 of 55 posts
Re: Show HN: Cactus Hybrid: We taught Gemma 4 to know when it's wrong
#12> "post-trained to know when it's wrong"
Is it also post-trained to know when it's wrong about when it's wrong?
> "Every response comes with a confidence score between 0 and 1"
How confident is it in its confidence?
Please, I'm sure that what you're doing is very neat and useful, but use other language to describe it. I beg you. You can't know when you're wrong. You can only know when you're unsure or inconsistent. You can be absolutely certain and still wrong and uncertain and still correct.
Re: Show HN: Cactus Hybrid: We taught Gemma 4 to know when it's wrong
#13> "post-trained to know when it's wrong" Is it also post-trained to know when it's wrong about when it's wrong? > "Every response comes with a confidence score between 0 and 1" How confident is it in its confidence? Please, I'm sure that what you're doing is very neat and useful, but use other language to describe it. I beg you. You can't know when you're wrong. You can only know when you're unsure or inconsistent. Y…
IMHO this also depends on the type of assertion.. For example, one system defines three broad classes of assertion : pure opinion (I like green); factual references (the current temperature here is 20c) ; and the rest in a catch-all about "reasoned judgements"
Complex assertions and their compounded forms can be filtered by these classes fairly easily. I rarely see this referenced in general comments.
Re: Show HN: Cactus Hybrid: We taught Gemma 4 to know when it's wrong
#14Does the model quality become degraded in other ways?
Re: Show HN: Cactus Hybrid: We taught Gemma 4 to know when it's wrong
#15> "post-trained to know when it's wrong" Is it also post-trained to know when it's wrong about when it's wrong? > "Every response comes with a confidence score between 0 and 1" How confident is it in its confidence? Please, I'm sure that what you're doing is very neat and useful, but use other language to describe it. I beg you. You can't know when you're wrong. You can only know when you're unsure or inconsistent. Y…
IMHO this also depends on the type of assertion.. For example, one system defines three broad classes of assertion : pure opinion (I like green); factual references (the current temperature here is 20c) ; and the rest in a catch-all about "reasoned judgements" Complex assertions and their compounded forms can be filtered by these classes fairly easily. I rarely see this referenced in general comments.
> pure opinion (I like green)
"I like green" is a statement of fact about what you like. "Green is good" would be an opinion. It's funny to me how often people mix the two.
> forms can be filtered by these classes fairly easily
Obviously not so easily. :)
Re: Show HN: Cactus Hybrid: We taught Gemma 4 to know when it's wrong
#16Earlier quoted context omitted.
IMHO this also depends on the type of assertion.. For example, one system defines three broad classes of assertion : pure opinion (I like green); factual references (the current temperature here is 20c) ; and the rest in a catch-all about "reasoned judgements" Complex assertions and their compounded forms can be filtered by these classes fairly easily. I rarely see this referenced in general comments.
> pure opinion (I like green) "I like green" is a statement of fact about what you like. "Green is good" would be an opinion. It's funny to me how often people mix the two. > forms can be filtered by these classes fairly easily Obviously not so easily. :)
opinion is ephemeral, cannot be independently confirmed or denied; purely single viewer information sounds like not-a-fact to me
Opinion is a ghost in the machine—fleeting, unanchored, and vanishing upon inspection. It leaves no footprint for another mind to verify, no independent trail of evidence to confirm or deny its existence. To rely on such solitary perception is to drift in a void where facts do not exist; it is not merely uncertainty, but an absence of reality itself—a whisper that the universe refuses to echo back. --AI Carl Sagan
Re: Show HN: Cactus Hybrid: We taught Gemma 4 to know when it's wrong
#17[dead]
Re: Show HN: Cactus Hybrid: We taught Gemma 4 to know when it's wrong
#18Earlier quoted context omitted.
> pure opinion (I like green) "I like green" is a statement of fact about what you like. "Green is good" would be an opinion. It's funny to me how often people mix the two. > forms can be filtered by these classes fairly easily Obviously not so easily. :)
opinion is ephemeral, cannot be independently confirmed or denied; purely single viewer information sounds like not-a-fact to me Opinion is a ghost in the machine—fleeting, unanchored, and vanishing upon inspection. It leaves no footprint for another mind to verify, no independent trail of evidence to confirm or deny its existence. To rely on such solitary perception is to drift in a void where facts do not exist; it…
It seems to me trivial to verify: just ask.
Re: Show HN: Cactus Hybrid: We taught Gemma 4 to know when it's wrong
#19> "post-trained to know when it's wrong" Is it also post-trained to know when it's wrong about when it's wrong? > "Every response comes with a confidence score between 0 and 1" How confident is it in its confidence? Please, I'm sure that what you're doing is very neat and useful, but use other language to describe it. I beg you. You can't know when you're wrong. You can only know when you're unsure or inconsistent. Y…
Interesting question and I don’t share your pessimism. Feels like it’s a matter of some plain old Bayesian stats, almost a homework assignment given all experimental data is available and known.
Re: Show HN: Cactus Hybrid: We taught Gemma 4 to know when it's wrong
#20> "post-trained to know when it's wrong" Is it also post-trained to know when it's wrong about when it's wrong? > "Every response comes with a confidence score between 0 and 1" How confident is it in its confidence? Please, I'm sure that what you're doing is very neat and useful, but use other language to describe it. I beg you. You can't know when you're wrong. You can only know when you're unsure or inconsistent. Y…
A few years ago, before RLVR became ubiquitous, people were using generate -> classify loops to get models to improve math reasoning. Turns out classification is sometimes easier to do and more accurate than generating coherent traces. So you'd get a model to "think step by step", then run each step (.split('/n/n')) through a classifier, and tell the model "this step might be wrong, re-check". If you're interested I could probably dig up some papers on this.
Now there might be even better ways of getting feedback, I saw some interesting trials using "J-spaces" (from Anthropic's latest research in this area). Turns out you can kinda see when the model uses deep seeded concepts in early layers, or it's "riffing on an idea" with shallow signals in those same layers. And youc an get some signal out of it, and have it re-do a step.
It's also worth mentioning that LMs are wrong in different ways from humans. It's not impossible that we'll eventually find ways of better understanding this (through mechanistic interpretation or something else) and have easy "classifiers" for "this comes from the training data" vs. "this comes from early context" (i.e. supplied materials from prompts/discovery) vs. "this comes from later tokens, likely the model doom-looped itself".