Claude 4's system prompt was published and contains:

"Claude’s reliable knowledge cutoff date - the date past which it cannot answer questions reliably - is the end of January 2025. It answers all questions the way a highly informed individual in January 2025 would if they were talking to someone from {{currentDateTime}}, "

https://docs.anthropic.com/en/release-notes/system-prompts#m...

I thought best guesses were that Claude's system prompt ran to tens of thousands of tokens, with figures like 30,000 tokens being bandied about.

But the documentation page linked here doesn't bear that out. In fact the Claude 3.7 system prompt on this page clocks in at significantly less than 4,000 tokens.

they arent.

a model learns words or tokens more pedantically but has no sense of time nor cant track dates

Yup. Either the system prompt includes a date it can parrot, or it doesn't and the LLM will just hallucinate one as needed. Looks like it's the latter case here.

Technically they don’t, but OpenAI must be injecting the current date and time into the system prompt, and Gemini just does a web search for the time when asked.

right but that's system prompting / in context

not really -trained- into the weights.

the point is you can't ask a model what's his training cut off date and expect a reliable answer from the weights itself.

closer you could do is have a bench with -timed- questions that could only know if had been trained for that, and you'd had to deal with hallucinations vs correctness etc

just not what llm's are made for, RAG solves this tho

What would the benefits be of actual time concepts being trained into the weights? Isn’t just tokenizing the dates and including those as normal enough to yield benefits?

E.g. it probably has a pretty good understanding between “second world war” and the time period it lasted. Or are you talking about the relation between “current wall clock time” and questions being asked?

there's actually some work on training transformer models on time series data which is quite interesting (for prediction purposes)

see google TimesFM: https://github.com/google-research/timesfm

what i mean i guess is llms can -reason- linguistically about time manipulating language, but can't really experience it. a bit like physics. thats why they do bad on exercises/questions about physics/logic that their training corpus might not have seen.

OpenAI injects a lot of stuff, your name, sub status, recent threads, memory, etc

sometimes its interesting to peek up under the network tab on dev tools

strange they would do that client side

Different teams who work backend/frontend surely, and the people experimenting on the prompts for whatever reason wanna go through the frontend pipeline.

its just like extra metadata associated with your account not much else