30 points Aldus551 2 days ago 15 comments
garrickvanburen 53 minutes ago | parent
jakeinspace 40 minutes ago | parent
verisimi 39 minutes ago | parent
However, it is then on the person asking the query to refine the query and push for more specifics.
I don't see the problem. Ai doesn't need to get it all right, first time.
darepublic 25 minutes ago | parent
Forgeties79 23 minutes ago | parent
Yes it kind of does or it’s not what we were promised/sold. A tool has to work reliably. I don’t want a calculator that’s correct most of the time.
foobar10000 10 minutes ago | parent
sdenton4 38 minutes ago | parent
asr 32 minutes ago | parent
slfnflctd 29 minutes ago | parent
As I see it, there are far greater concerns about guardrails being baked in - possibly at the request of poorly informed government officials - cordoning off multiple broad categories of knowledge needlessly. Which is what I thought this post was going to be about.
deadlast2 22 minutes ago | parent
snvzz 14 minutes ago | parent
Handcuffs, for your external brain.
Tade0 12 minutes ago | parent
This used to happen a lot in LLMs as recent as Q1 2026 in programming tasks: if something was too far off the beaten path, the model would misinterpret the intention.
Nowadays I'm noticing that while the solution is what I asked for, it's fairly roundabout and verbose. Being more specific in prompts doesn't help.
YetAnotherNick 12 minutes ago | parent