HNHacker News
TopNewBestAskShowJobs

genrader

1 karma · joined February 14, 2024

submissionscomments
genrader··on Fable 5.1 Solves the Cyphral Distich, a 370-year-old cipher
Correct but it's never been so accessible, so easy so smart and easy for the population of the world to use
genrader··on Registration without a phone number on Signal will use zero-knowledge proofs
You wouldn't believe the spam if they did that
genrader··on Why is Google still serving dodgy ads?
This is untrue and you have to be at least 80%
genrader··on Gemini 3 Pro: the frontier of vision AI
If you're using for instance the Gemini web app there may be a preference in the system prompt to immediately favor the fact that you said to create an image when in fact it may have been better to initially start with a regular chat prompt, making sure you're on Gemini 3 Pro thinking, and then give it exactly what you usually would. You can tell it that after it has an answer to the question then to create an image for it.

This may even work if you tell it to do all that prior to figuring out what to create for the image,

genrader··on Gemini 3 Pro: the frontier of vision AI
Go watch some of the more recent Google developer, Google AI, and Google deepmind videos, they're all separate channels at YouTube but try to catch some from the last 6 months with some of these explanatory topics on the developer side that are philosophical/ mathematical enough to explain this to you without going into the gritty details and should answer your question
genrader··on Gemini 3 Pro: the frontier of vision AI
You're correct, however midwit people who don't actually fully understand all of this will latch on to one of the early difficult questions that was shown as an example, and then continued to use that over and over without really knowing what they're doing while the people developing the model and also testing the model are doing far more complex things
genrader··on Gemini 3 Pro: the frontier of vision AI
Google's summary of the thinking process isn't as detailed or accurate as what is actually being thought out.

For instance, look at what other reasoning models show you about their thinking. You can tell Gemini is not giving it all to you, so I don't put full trust in it unless it routinely is giving me an issue that I can catch in there.

For instance, it doesn't show you all the tool use that it can use nor distinguish the different types where I really wish it would. Especially because I force it to in a Gemini personal context instruction as well as many prompts and it does do them

genrader··on Gemini 3 Pro: the frontier of vision AI
This is an excellent short way to understand that what you give Gemini 3 Pro is substantial better in understanding the data.

Making sure you ask correctly how it should give you the info is still lacking in many people's ability

genrader··on Claude for Excel
you should:

-stop using the free plan -don't use gemini flash for these tasks -learn how to do things over time and know that all ai models have improved significantly every few months

genrader··on Claude for Excel
This is so correct it hurts
genrader··on Occult books digitized and put online by Amsterdam’s Ritman Library
What did I just read
genrader··on Occult books digitized and put online by Amsterdam’s Ritman Library
No, because one built a civilization and the other is actual nonsense