top | item 47075730 (no title) chermi | 10 days ago You can really notice the tool use problems. They gotta get on that. The agent trend seems real, and powerful. They can't afford to fall behind on it. discuss order hn newest verdverm|10 days ago I don't really have tool usage issues that I don't put under that doesn't follow system prompt instructions consistentlythere are these times where it puts a prefix on all function calls, which is weird and I think hallucination, so maybe that one3.1 hopefully fixes that HardCodedBias|10 days ago "They can't afford to fall behind on it."They are very, very seriously far behind as of 3.0.We'll see if 3.1 addresses the issue at all.
verdverm|10 days ago I don't really have tool usage issues that I don't put under that doesn't follow system prompt instructions consistentlythere are these times where it puts a prefix on all function calls, which is weird and I think hallucination, so maybe that one3.1 hopefully fixes that
HardCodedBias|10 days ago "They can't afford to fall behind on it."They are very, very seriously far behind as of 3.0.We'll see if 3.1 addresses the issue at all.
verdverm|10 days ago
there are these times where it puts a prefix on all function calls, which is weird and I think hallucination, so maybe that one
3.1 hopefully fixes that
HardCodedBias|10 days ago
They are very, very seriously far behind as of 3.0.
We'll see if 3.1 addresses the issue at all.