Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Only 1 LLM can fly a drone

github.com

Post reply on HN
Print view View original

91–100 of 100 posts

Re: Show HN: Only 1 LLM can fly a drone

#91

Post by volkercraig »

lukan wrote: post #83
volkercraig wrote: post #53

Earlier quoted context omitted.

They are text generators, and yes they are pretty good, but that really is all they are, they don't actually learn, they don't actually think. Every "intelligence" feature by every major AI company relies on semantic trickery and managing context windows. It even says it right on the tin; Large LANGUAGE Model. Let me put it this way: What OP built is an airplane in which a pilot doesn't have a control stick, but they…

"they don't actually learn" Give the LLM agent write acces to a text file to take notes and it can actually learn. Not really realiable, but some seem to get useful results. They ain't just text generators anymore. (but I agree that it does not seem the smartest way to control a plane with a keyboard)

If thats youre definition of learning, my casio FX has an "ans" feature that "learns" from earlier calculations!!

Re: Show HN: Only 1 LLM can fly a drone

#92

Post by famouswaffles »

nrrbtrbbrb wrote: post #88
notepad0x90 wrote: post #71

Earlier quoted context omitted.

LLMs can do chat-completion, they don't do only chat completion. There are LLMs for image generation, voice generation, video generation and possibly more. The camera of a drone inputs images for the LLM, then it determines what action take based on that. Similar to if you asked ChatGPT "there is a tree in this picture, if you were operating a drone, what action would you take to avoid collision", except the "there i…

> There are LLMs for image generation, That part isn’t handled by an LLM > voice generation, That part isn’t handled by an LLM > video generation That part isn’t handled by an LLM

Yes it can be, and often is. Advanced voice mode in chatGPT and the voice mode in Gemini are LLMs. So is the image gen in both chatGPT and Gemini (Nano Banana).

Re: Show HN: Only 1 LLM can fly a drone

#94

Post by lukan »

volkercraig wrote: post #91
lukan wrote: post #83

Earlier quoted context omitted.

"they don't actually learn" Give the LLM agent write acces to a text file to take notes and it can actually learn. Not really realiable, but some seem to get useful results. They ain't just text generators anymore. (but I agree that it does not seem the smartest way to control a plane with a keyboard)

If thats youre definition of learning, my casio FX has an "ans" feature that "learns" from earlier calculations!!

Can that "ans" variable influence the general way your casio does future calculations?

I don't think so. But with a AI agent it can.

Sure, they still don't have real understanding, but calling this technology mere text generators in 2026 seems a bit out of the loop.

Re: Show HN: Only 1 LLM can fly a drone

#95

Post by general_reveal »

avaer wrote: post #24

Gemini 3 is the only model I've found that can reason spatially. The results here are accurate to my experiments with putting LLM NPCs in simulated worlds. I was surprised that most VLLMs cannot reliably tell if a character is facing left or right, they will confidently lie no matter what you do (even gemini 3 cannot do it reliably). I guess it's just not in the training data. That said Qwen3VL models are smaller/fas…

We just need to fine tune these models on Ocarina of Time Water Temple - spatial reasoning solved.

Re: Show HN: Only 1 LLM can fly a drone

#96

Post by calchiwo »

The detection prepass plus text reasoning pipeline is effectively a perception to symbol translation layer, and that is where most of the brittleness will hide. Once you collapse a continuous 3D scene into discrete labels, you lose uncertainty, relative geometry, and temporal consistency unless you explicitly model them. The LLM then reasons over a clean but lossy world model, so action quality is capped by what the detector chose to surface.

The failure mode is not just missed objects, it is state aliasing. Two physically different scenes can map to the same label set, especially with occlusion, depth ambiguity, or near boundary conditions. In control tasks like drone navigation, that can produce confident but wrong actions because the planner has no access to the underlying geometry or sensor noise. Error compounds over time since each step re-anchors on an already simplified state.

Are you carrying forward any notion of uncertainty or temporal tracking from the vision stage, or is each step a stateless label snapshot fed to the reasoning model?

Re: Show HN: Only 1 LLM can fly a drone

#98

Post by Bender »

LLM's seem like the wrong platform to operate a drone in my opinion. I would expect that to be something more like a gaming engine. It should be small, simple, low latency and maybe based on a first person shooter running on insane difficulty. Small enough to fit in a tiny firmware space. It should boot so fast the firmware could be upgraded mid-flight without missing a beat. Give it simple friend or foe and obliterate anything not green.

Re: Show HN: Only 1 LLM can fly a drone

#99

Post by notepad0x90 »

nrrbtrbbrb wrote: post #88
notepad0x90 wrote: post #71

Earlier quoted context omitted.

LLMs can do chat-completion, they don't do only chat completion. There are LLMs for image generation, voice generation, video generation and possibly more. The camera of a drone inputs images for the LLM, then it determines what action take based on that. Similar to if you asked ChatGPT "there is a tree in this picture, if you were operating a drone, what action would you take to avoid collision", except the "there i…

> There are LLMs for image generation, That part isn’t handled by an LLM > voice generation, That part isn’t handled by an LLM > video generation That part isn’t handled by an LLM

What is it handled by? I'm honestly curious, there are models specifically labeled as for those tasks.

Re: Show HN: Only 1 LLM can fly a drone

#100

Post by laffOr »

notepad0x90 wrote: post #70
laffOr wrote: post #36

Earlier quoted context omitted.

There are two different things: 1. a drone that you can talk to and fly on its own 2. a drone where the flying is controlled by an LLM (2) is a specific instance of the larger concept of (1). You make an argument that 1 should be addressed, which no one is denying in this thread - people are arguing that (2) is a bad way to do (1).

You're considering "talking to" a separate thing, I consider it the same as reading street signs or using object recognition. My voice or text input is just one type of input. Can other ML solutions or algorithms detect a tree (same as me telling it there is a tree,yaw to the right), yes, can LLMs detect a tree and determine what course of action to take? also true. Which is better? I don't know, but I won't be quick…

Definitely maybe - but then we are discussing (2), i.e. "what is the right technical solution to solve (1)".

Your previous comment was arguing that (1) is great (which no one denies in this thread, and it is a different discussion about what products are desirable rather than how to build said product) in an answer to someone arguing (2).

Post reply on HN