Hacker News new | past | comments | ask | show | jobs | submit
Tiberium | on: Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots
Funny result from the web demo. I'm well aware that it's an extremely small and, well, stupid, model, but even so:

Query: HN

Result:

{ "function_calls": [ { "name": "lock_door", "arguments": { "door": "front door" } } ], "reasoning": "User wants to lock the door. No specific door mentioned, so use 'front door' as default.", "confidence": 0 }

I'd expect it to at least ignore (call no tools) for the queries that it doesn't understand. And it seems like it does do that, just not consistently.

yoavm | parent | next
The website says the model is for "tool calling, device use, and structured extraction". Your example just doesn't seem to be very relevant. FWIW, it did a pretty good job for tool calling when I tried it, and I think it could be pretty nice to have this running on locally and integrate with Home Assistant.
evmaki | root | parent | next
False positives are definitely relevant and worth measuring - natural language interfaces always have a discoverability problem, i.e., users not knowing what actions the system does and does not support. If the frontend of that system lacks the ability to reject unsupported commands, weird stuff happens.

Nonetheless, this is very cool work! If I can offer a small suggestion to the team at Cactus, it would be to evaluate your releases on some usability criteria (including false positives). Any serious integrator or adopter of these models would want to have that information available.

jdknezek | root | parent | next
> "confidence": 0

OP and the linked page talk about the confidence score and using it as an action threshold, so it looks like an appropriate total response to me.

evmaki | root | parent
Right, but that's not the same thing as reporting a benchmark across a test set. It doesn't help me determine how well the model does across a decently-large sample size of commands. It doesn't tell me with what reliability the confidence will be below a given threshold when it should be, above that threshold when it should be, etc.
loading story #49253881
curious_cat_163 | root | parent
I think the test above is about tool calling... That's how I read it. The issue here is known as "out of distribution detection" in the old-timey classification world.

I am not sure how a micro model will fundamentally solve it. Would love to understand what dannyw and team did there?

derangedHorse | root | parent
How did you draw an association between dannyw and Cactus? There are no 'Danny's on the list of GH contributors nor is there one named in the paper. Just curious.
petu | parent | next
"confidence": 0, so I guess you could threshold it
loading story #49253452
loading story #49254801
jszymborski | parent | next
no, this is the appropriate response to hearing the words "HN" :P
plingbang | parent | next
I've got an identical output with the prompt "do not lock the door".
hmokiguess | parent | next
yeah I got the same, almost like its biased heavily towards that as the 0 ranking -- my prompt was just the word 'potato'
Schiendelman | parent | next
Was that the first message you sent it?
HenryNdubuaku | parent | next
This is exactly why the confidence feature was introduced, the model knows when its wrong, we could hide that part and return a placeholder "sorry I only do function calls", would that be better or you prefer to see everything?