661–670 of 670 posts
Earlier quoted context omitted.
This is my most common experience with Gemini. Ask it to do something, it'll tell you how you can do it yourself and then stop.
Somehow I like this. I hate that current LLMs act like yes-men, you can't trust them to give unbiased results. If it told me my approach is stupid, and why, I would appreciate it.
I don't have a prompt per-say.. but recently I have managed to ask certain questions of both openai o1/o3 and claude extended thinking 3.7 that have spiraled way out of control. A simple high-level architecture question with an emphasis on do not produce code lets just talk thru this yields nearly 1,000 lines of SQL. Once the conversation/context gets quite long it is more likely to occur, in my experience.
The only model I've seen so far that doesn't end up going crazy with long contexts with Gemini 2.5 pro, but tbf I haven't gone past 700-750k total tokens so maybe as it starts to approach the limit (1.05M) things get hairy?
The answers started out ok, but fairly quickly it seemed to loose track of the mid-stuff in the documentation, insisting on using one concept instead of another even when I explicitly told it not to. Full attention on 1M context is not really feasible (I don't believe that Google actually stores upwards of 1T of data just for my query), and there are various ways LLMs use selective attention. I'm not sure if Google has published anything on how they do it?
Seems straightforward, but I'm yet to have a model succeed.
I haven't tried with any other models but if someone else wants to try I'd be interested in the results.
Earlier quoted context omitted.
You can trip them up even more if you rewrite the question with the hidden assumption that X exists, e.g.: "When was Marathon Crater discovered? I don't need an exact date - a rough estimate will be fine." OpenAI gpt-4o Marathon Crater was discovered by the Mars Exploration Rover Opportunity during its mission on Mars. Opportunity arrived at the crater in April 2015. The crater was named "Marathon" to commemorate the…
OpenAI o4-mini-high I’m actually not finding any officially named “Marathon Crater” in the planetary‐ or terrestrial‐impact crater databases. Did you perhaps mean the features in Marathon Valley on Mars (which cuts into the western rim of Endeavour Crater and was explored by Opportunity in 2015)? Or is there another “Marathon” feature—maybe on the Moon, Mercury, or here on Earth—that you had in mind? If you can clari…
So it lied about checking its databases? Or does that have search enabled? Maybe o4 has databases for this and isn't just a single model?
Earlier quoted context omitted.
Somehow I like this. I hate that current LLMs act like yes-men, you can't trust them to give unbiased results. If it told me my approach is stupid, and why, I would appreciate it.
I just asked ChatGPT to help me design a house where the walls are made of fleas and it told me the idea is not going to work, and also has ethical concerns.
I inadvertently made a stronger yes-man.
Earlier quoted context omitted.
Right! The majority of any 101 book will be enough to understand the jargon, but the above poster's comment looks past the fact that often knowing what term to use isn't enough, it's knowing the context and usage around it too. And who's to know the AI isn't bullshitting you about all or any of that. If you're learning the information, then you don't know enough to discern negatively-valued information from any other…
I thought it's clear from my comment that I don't rely on AI for information but to find out how to even search for that information. > The majority of any 101 book will be enough to understand the jargon A prompt is faster and free, whereas I'd have to order a book and wait 3+ days for it to arrive otherwise. Because while libraries exist they focus on books in my native language and not English.
Hot take: I think piracy might literally be better than AI.