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 of a problem these days.

▲

NegativeLatency 6 minutes ago | parent | next [-]

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.

▲

super256 3 hours ago | parent | prev | next [-]

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 (which is why e.g. Kagi charges a few bucks for search every month).

▲

Catloafdev 2 hours ago | parent [-]

It's not strictly compute, because this has noticeably improved in open-weight models too, such as Gemma and Qwen. I suspect they noticed this issue and adjusted their training to be better about it over time.

	▲	ahmedfromtunis an hour ago \| parent [-]
		I built a toy news-summarizing agent with Gemma 4, and it was so frustrating, actually, because of the cut-off date. The model wasted over half the token budget, each time, on internal debates over the current date. When generating a World Cup summary, for example, it refused to believe qualification rounds were over and refused to even call the web searching tool to collect the data. I injected the current datetime at the very beginning of the system prompt, but Gemma refused to believe it! The m-effer insisted the timestamp was fake and hypothesized it was being evaluated in a synthetic lab test with simulated future dates! No amount of system prompting could convince it to trust the clock. That was the most frustrating and bizarre "bug" I ever faced!

▲

InsideOutSanta 3 hours ago | parent | prev | next [-]

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 from training data.

	▲	NegativeLatency 5 minutes ago \| parent [-]
		I find they generally do ok, but a few lines in an AGENTS.md or manual prompting to verify stuff against current docs/source, and check for current version of software helps a lot.

▲

Isamu an hour ago | parent | prev [-]

>the model said that’s pure fiction.

Were you expecting your model to be updated on current events? Why?

Also the specific event you are referring to is a statistically very improbable event, prior to its actually happening.

>It only acquiesced when I specifically directed it to check Reuters.

Do all models do this? They check in with Reuters? Why would a model think that you asking about an extremely improbable event warranted reaching out to Reuters?

▲

gjskngnf an hour ago | parent | next [-]

I was not expecting model weights to be updated on current events.

It’s clearly warranted because a model that trusts its weights on current events will give an outdated answer. Extremely improbable events happen all the time.

	▲	xienze 37 minutes ago \| parent [-]
		I think the models are trying to optimistically avoid doing web searches, because they're surprisingly a lot harder to do well than you'd think.

▲

mywittyname an hour ago | parent | prev [-]

He asked it to double check. It's reasonable to expect the LLM to handle that trivial task.