[flagged]
Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots
191–200 of 214 posts
Re: Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots
#192Earlier quoted context omitted.
Tested your example, the confidence is 0. In smart home context, I can think of an application where the low confidence answers can be forwarded to cloud, whereas the vast majority generic queries solved locally, if the confidence is reliable enough. The response is quite fast by the way.
But this isn’t a query that should need to be forwarded to the cloud for acting on!
Considering this is a 14MB model running almost in a microcontroller, I am fine with such ‘ambigiuous’ queries cannot be handled, as long as the model confidence score is accurate. By the way, I did not test this model thoroughly. I am speculating on the potential of a small model like this. I don’t know if this one is good enough or not.
Re: Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots
#193Earlier quoted context omitted.
But this isn’t a query that should need to be forwarded to the cloud for acting on!
I don't know, the back of my napkin says you'll need consensus of at least three servers in order to complete the command.
It is a 14MB model. You don’t need servers to run it. Check your napkin well.
Re: Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots
#194Earlier quoted context omitted.
Fwiw people have told me that GPT2 doesn’t qualify as an LLM at 550MB despite being one of the first LLMs. So the practical answer to your question is: not much.
I don't think some people are aware that "large" has always referred to the training inputs not resulting the size of the model. LLM is not "we made a language model and it is big" -- it's "we trained this model on a lot of language"
Not aware of that etymology
Re: Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots
#195My first query: > Make it a little warmer in here. The reply: > "name": "set_thermostat", > "arguments": { > "temperature": 65, > "mode": "cool", > ... > "reasoning": "'warmer' implies need for cooling; set_thermostat with temperature 65 (typical warmth) and mode 'cool'.", Maybe I'm doing it wrong?
but wouldn't it need to know the current temp for that to work? my understanding was that the model is best at tool calling
In what world would this make any sense at any temperature?
> 'warmer' implies need for cooling
Re: Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots
#196> set lights on
{ "function_calls": [ { "name": "set_lights", "arguments": { "room": "bedroom", "state": "on" } } ], "confidence": 0 }
is confidence 0 that its confident?
Re: Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots
#197Funny 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 doe…
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?
confidently stating that the confidence is right seems like a big claim
Re: Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots
#198[flagged]
Re: Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots
#199What’s one of the most impressive usecase or example?
Re: Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots
#200Earlier quoted context omitted.
I don't know, the back of my napkin says you'll need consensus of at least three servers in order to complete the command.
It is a 14MB model. You don’t need servers to run it. Check your napkin well.
I am sorely dissappointed that the state of the internet has become such that my sarcasm was not only possibly but actually missed.