Hacker News Reader

Comment by radicality | Hacker News Reader

How do I get Gemini to be more proactive in finding/double-checking itself against new world information and doing searches?

For that reason I still find chatgpt way better for me, many things I ask it first goes off to do online research and has up to date information - which is surprising as you would expect Google to be way better at this. For example, was asking Gemini 3 Pro recently about how to do something with a “RTX 6000 Blackwell 96GB” card, and it told me this card doesn’t exist and that I probably meant the rtx 6000 ada… Or just today I asked about something on macOS 26.2, and it told me to be cautious as it’s a beta release (it’s not). Whereas with chatgpt I trust the final output more since it very often goes to find live sources and info.

View on HN

Gemini is bad at this sort of thing but I find all models tend to do this to some degree. You have to know this could be coming and give it indicators to assume that it’s training data is going to be out of date. And it must web search the latest as of today or this month. They aren’t taught to ask themselves “is my understanding of this topic based on info that is likely out of date” but understand after the fact. I usually just get annoyed and low key condescend to it for assuming its old ass training data is sufficient grounding for correcting me.

That epistemic calibration is is something they are capable of thinking through if you point it out. But they aren’t trained to stop and ask/check themselves on how confident do they have a right to be. This is a meta cognitive interrupt that is socialized into girls between 6 and 9 and is socialized into boys between 11-13. While meta cognitive interrupt to calibrate to appropriate confidence levels of knowledge is a cognitive skill that models aren’t taught and humans learn socially by pissing off other humans. It’s why we get pissed off st models when they correct ua with old bad data. Our anger is the training tool to stop doing that. Just that they can’t take in that training signal at inference time

Yeah any time I mention GPT-5, the other models start having panic attacks and correcting it to GPT-4. Even if it's a model name in source code!

They think GPT-5 won't be released until the distant future, but what they don't realize is we have already arrived ;)

Reply on news.ycombinator.com