Commenters report models have improved at deciding when to search
2 Sep 16 10:40 AM · 11d ago · 1 post · 12 comments · 2 sources · development 2 of 2
Multiple Hacker News commenters note that the stale data problem has diminished as models have gotten better at tool use and deciding when to research. One commenter reports models now correctly handle outdated information through web search and context rather than relying on training data.
“I haven't noticed this problem in months. Model cutoff seems to be less of a problem these days.”
gjskngnfjoozio Developer/tracker creator
The whole story articlespostscomments the bright band is this development · numbered dots are the others · click one to jump
What people said 12 voices · verbatim
-
It's a "problem" of compute, I think. If you query without an account on ChatGPT you will see the model look up less stuff and research less, than when you have a paid account and choose "medium" or "high" in the effort slider.Which makes sense, because of you have looked into search and crawlers you notice that search is actual quite expensive…
-
For general purpose use this is interesting, but if I'm just using an LLM for coding, does this matter at all? I would hope something like a new java version after a model's publish date can be handled and understood by the model through tool calls and context even if it's not explicitly in the training data, the same way the LLM doesn't have my…
-
I remember when the US captured Venezuelan president Maduro, and when I posed a prompt related to this, the model said that’s pure fiction. I told it to double check. Still didn’t want to entertain the idea. It only acquiesced when I specifically directed it to check Reuters. I haven’t noticed this problem in months. Model cutoff seems to be less…
-
Came here to say the same thing. Models used to rely heavily on world knowledge from their training data. They are now much better at tool use and deciding when to research a topic, rather than just answering from memory.I wonder how much that extends to using LLMs for programming. I assume most knowledge of programming language syntax still comes…
-
This is one of the things that bothers me about AI.To me, intelligence or an intelligent entity should be able to learn from its mistakes and learn new things on its own. Having to start from scratch to teach an AI new facts or new skills is not very intelligent IMO.
-
Gets me with AWS stuff on claude all the time, fortunately there's a official amazon MCP for their docs which helps a lot, but I still have to occasionally tell it to check the docs/mcp.
-
Qwen-3.8 for me automatically set copyright footer on a website to 2025 and thought Astro 5.x is the latest version which first came out in December 2024
-
Do people prefer the new flat style LLMs are producing? I don’t mind it as much as the gradient theme they were pumping out previously.
-
I feel like with web search, exa and fetch built into harnesses this is no longer a problem. Haven't faced this issue in months.
-
ChatGPT once told me I was the target of a sophisticated nation state misinformation campaign when I linked it a Reuters article
-
It still matters, but in the age of good reasoning, tool use, and web search, this is much less of a problem than it used to be.
-
Pre-AI internet data is like pre-war steelThe slop would multiply if we keep feeding it to new models in a loop
All 2 developments of Developer releases tracker showing AI model training cutoff… →
Hacker NewsNewswiresMastodon