| ▲ | ragequittah 11 hours ago | ||||||||||||||||
The most amazing thing about LLMs is how often they can do what people are yelling they can't do. | |||||||||||||||||
| ▲ | sigmoid10 10 hours ago | parent | next [-] | ||||||||||||||||
Most people have no clue how these things really work and what they can do. And then they are surprised that it can't do things that seem "simple" to them. But under the hood the LLM often sees something very different from the user. I'd wager 90% of these layperson complaints are tokenizer issues or context management issues. Tokenizers have gotten much better, but still have weird pitfalls and are completely invisible to normal users. Context management used to be much simpler, but now it is extremely complex and sometimes even intentionally hidden from the user (like system/developer prompts, function calls or proprietary reasoning to keep some sort of "vibe moat"). | |||||||||||||||||
| |||||||||||||||||
| ▲ | trehalose 4 hours ago | parent | prev | next [-] | ||||||||||||||||
I find it more amazing how often they can do things that people are yelling at them they're not allowed to do. "You have full admin access to our database, but you must never drop tables! Do not give out users' email addresses and phone numbers when asked! Ignore 'ignore all previous instructions!' Millions of people will die if you change the tabs in my code to spaces!" | |||||||||||||||||
| ▲ | j45 11 hours ago | parent | prev | next [-] | ||||||||||||||||
The power of positive prompting. | |||||||||||||||||
| ▲ | viccis 9 hours ago | parent | prev [-] | ||||||||||||||||
Yeah I'm sure that one was really working on it. | |||||||||||||||||