711–720 of 998 posts
Earlier quoted context omitted.
Opus 4.6: Walk! At 50 meters, you'll get there in under a minute on foot. Driving such a short distance wastes fuel, and you'd spend more time starting the car and parking than actually traveling. Plus, you'll need to be at the car wash anyway to pick up your car once it's done.
Lmao, and this is what they are saying will be an AGI in 6 months?
Earlier quoted context omitted.
Unless the LLM is a base model or just a finetuned base model, it definitely doesn't predict words just based on how likely they are in similar sentences it was trained on. Reinforcement learning is a thing and all models nowadays are extensively trained with it. If anything, they predict words based on a heuristic ensemble of what word is most likely to come next in similar sentences and what word is most likely to…
> If anything, they predict words based on a heuristic ensemble of what word is most likely to come next in similar sentences and what word is most likely to give a final higher reward. So... "finding the most likely next word based on what they've seen on the internet"?
Earlier quoted context omitted.
The Lojban language already exists and allows for eliminating ambiguity. It's obviously not practical for general use, though. https://en.wikipedia.org/wiki/Lojban
Lojban is syntactically unambitious. Semantically it's still just as vague as any natural language.
https://www.linkedin.com/posts/yuvalmerhav_claude-activity-7...
I've used LLMs enough that I have a good sense of their _edges_ of intelligence. I had assumed that reasoning models should easily be able to answer this correctly. And indeed, Sonnet and Opus 4.5 (medium reasoning) say the following: Sonnet: Drive - you need to bring your car to the car wash to get it washed! Opus: You'll need to drive — you have to bring the car to the car wash to get it washed! Gemini 3 Pro (mediu…
If I append 'think carefully' to the end of the prompt, it returns driving as the correct answer.
Earlier quoted context omitted.
By "patched", you can't mean they added something to the internal prompt to show it how to answer this one specific question?!
Absolutely. There is a preflight guardrail that steers specific words, phrases, concepts with tweaked output.
This trick went viral on TikTok last week, and it has already been patched. To get a similar result now, try saying that the distance is 45 meters or feet. The new one is with upside down glass: https://www.tiktok.com/t/ZP89Khv9t/
Ah yes, one of those novelty reversible cups.
Now shudder at the thought that people are pushing towards building more and more of the world's infrastructure with this kind of thinking.
IMO this is a great example of how we're often asking loaded questions without realizing it. IMO it's the same when we're asking: "Should I implement X from scratch, or import a small library to do it?" vs "Should I add feature X to the codebase or bring in another dependency for it?" In the first question, it sounds like a good idea to not reinvent the wheel, in the second it sounds bad to have dependency.
My experience with Chatbots outside of a coding context also ends up like this. A while ago I asked: Is "Read more" an appropriate project for the Getting things done framework? - The answer, yes, it was. Then I asked "Is Read More too big of a project to be appropriate for the GTD Framework" - The answer? Yes, it was far too big.
LLMs have another related bias though, which is a bit more subtle and easy to trip up on, which is that if you give options A or B, and then reorder it so it is B or A, the result may change. And I don't mean change randomly the distribution of the outcomes will likely change significantly.