Qwen3.5 has tool calling, so you can give it a wikipedia tool which it uses to know what happened in Tiananmen Square without issues =)

▲

troad 6 hours ago | parent | next [-]

That's very cool! I think giving it some research tools might be a nifty thing to try next. This is a fairly new area for me, so pointers or suggestions are welcome, even basic ones. :)

Worth adding that I had reasoning on for the Tiananmen question, so I could see the prep for the answer, and it had a pretty strong current of "This is a sensitive question to PRC authorities and I must not answer, or even hint at an answer". I'm not sure if a research tool would be sufficient to overcome that censorship, though I guess I'll find out!

	▲	theshrike79 4 hours ago \| parent [-]
		Basically ask any coding agent to create you a simple tool-calling harness for a local model and it'll most likely one-shot it. Getting the local weather using a free API like met.no is a good first tool to use.

▲

girvo 7 hours ago | parent | prev [-]

I'd recommend it too, because the knowledge cutoff of all the open weight Chinese models (M2.7, Qwen3.5, GLM-5 etc) is earlier than you'd think, so giving it web search (I use `ddgr` with a skill) helps a surprising amount

▲

theshrike79 7 hours ago | parent [-]

Yep, having a "stupid" central model with multiple tools is IMO the key to efficient agentic systems.

It needs to be just smart enough to use the tools and distill the responses into something usable. And one of the tools can be "ask claude/codex/gemini" so the local model itself doesn't actually need to do much.

▲

zozbot234 7 hours ago | parent | next [-]

> Yep, having a "stupid" central model with multiple tools is IMO the key to efficient agentic systems.

That doesn't fix the "you don't know what you don't know" problem which is huge with smaller models. A bigger model with more world knowledge really is a lot smarter in practice, though at a huge cost in efficiency.

▲

spockz 6 hours ago | parent | next [-]

Ive always wondered where the inflection point lies between on the one hand trying to train the model on all kinds of data such as Wikipedia/encyclopedia, versus in the system prompt pointing to your local versions of those data sources, perhaps even through a search like api/tool.

Is there already some research or experimentation done into this area?

▲

zozbot234 6 hours ago | parent [-]

The training gives you a very lossy version of the original data (the smaller the model, the lossier it is; very small models will ultimately output gibberish and word salad that only loosely makes some sort of sense) but it's the right format for generalization. So you actually want both, they're highly complementary.

	▲	spockz 5 hours ago \| parent [-]
		[dead]

▲

theshrike79 6 hours ago | parent | prev [-]

That's the key, it just needs to be smart enough to 1) know it doesn't know and 2) "know a guy" as they say =) (call a tool for the exact information)

Picking a model that's juuust smart enough to know it doesn't know is the key.

▲

susupro1 3 hours ago | parent | prev [-]

[dead]