Any instructions available for running this on an ESP32-S3 or P4 like the site says?
Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots
41–50 of 188 posts
Re: Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots
#42I tested with import needle @needle.tool def add(a: int, b: int): "Add two numbers." return a + b agent = needle.Needle(tools=[add]) print(agent.run("calculate 1 + 1?")["reasoning"]) python main.py No calculator or math tool available. conclusion: completly useless
Try the following tool description: "Calculate the sum of two numbers. Use for any arithmetic or math question." instead of "Add two numbers." Let me know how it goes, thanks!
Re: Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots
#43I tested with import needle @needle.tool def add(a: int, b: int): "Add two numbers." return a + b agent = needle.Needle(tools=[add]) print(agent.run("calculate 1 + 1?")["reasoning"]) python main.py No calculator or math tool available. conclusion: completly useless
Try the following tool description: "Calculate the sum of two numbers. Use for any arithmetic or math question." instead of "Add two numbers." Let me know how it goes, thanks!
It does better with clearer tool description, but we are taking note of these complaints for future improvements.
Re: Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots
#44Could someone please share how such open source micro-LLMs might have been created? Do the creators take something like DeepSeek, and then delete most of the neurons to whittle down the size?
Technically, you could do that, but we trained this one from the ground up!
Re: Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots
#45I tested with import needle @needle.tool def add(a: int, b: int): "Add two numbers." return a + b agent = needle.Needle(tools=[add]) print(agent.run("calculate 1 + 1?")["reasoning"]) python main.py No calculator or math tool available. conclusion: completly useless
Try the following tool description: "Calculate the sum of two numbers. Use for any arithmetic or math question." instead of "Add two numbers." Let me know how it goes, thanks!
works better that way, thanks :)
Re: Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots
#46Earlier quoted context omitted.
Try the following tool description: "Calculate the sum of two numbers. Use for any arithmetic or math question." instead of "Add two numbers." Let me know how it goes, thanks!
works better that way, thanks :)
Thanks, we shall improve this for the next release.
Re: Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots
#47Earlier quoted context omitted.
Try the following tool description: "Calculate the sum of two numbers. Use for any arithmetic or math question." instead of "Add two numbers." Let me know how it goes, thanks!
works better that way, thanks :)
but still struggle when changing the quesion:
import needle
@needle.tool
def add(a: int, b: int):
"Calculate the sum of two numbers. Use for any arithmetic or math question."
return a + b
agent = needle.Needle(tools=[add])
print(agent.run("what is 5 + 7?")["reasoning"])
Re: Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots
#48Re: Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots
#49Makes me think of the demo from some time ago where someone got a ~29M parameter model running on an esp32. I wonder what kind of throughput this could get if a handful of esp32s were strung together... Edit: I have a pile of d1 minis, but not much time.
That demo was Needle 1 indeed and we are creating the guide for ESP32 now as we speak.
Re: Show HN: Needle2: 14MB agentic LLM for phones, wearables, smart home and robots
#50I wonder if there's any way to get this to plan out a dag of tool calls? i.e. use the results from earlier calls as the parameters to later ones? I tried introducing a stack based system, but gave up pretty quickly.