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

Show HN: I made a Raspberry with Qwen my local car AI

github.com

Post reply on HN
Print view View original

41–50 of 79 posts

Re: Show HN: I made a Raspberry with Qwen my local car AI

#41

Post by HPsquared »

whalesalad wrote: post #26
ehnto wrote: post #14

Fair warning, I have found local models and frontier models to be very bad at the specifics when it comes to cars. Small differences like month and year model can impact oil capacity, oil weight and things like that, the details that matter quite a bit. I found frontier models couldn't get things like what engine was in a 1994 Nissan Skyline, one of the more infamous and talked about cars on internet forums for decad…

Just a few hours ago I gave ChatGPT my window sticker and the installation manual for a new suspension setup. I asked for new hardware that would typically be replaced during this install, like torque-to-yield bolts and fasteners. I also asked for new oil filters. I got a comprehensive grid of the exact part numbers needed in a nice dense table. sol 5.6 high is my daily driver.

You really need something smart enough to browse through the parts etc suppliers and find links.

Re: Show HN: I made a Raspberry with Qwen my local car AI

#43

Post by King-Aaron »

whalesalad wrote: post #26
ehnto wrote: post #14

Fair warning, I have found local models and frontier models to be very bad at the specifics when it comes to cars. Small differences like month and year model can impact oil capacity, oil weight and things like that, the details that matter quite a bit. I found frontier models couldn't get things like what engine was in a 1994 Nissan Skyline, one of the more infamous and talked about cars on internet forums for decad…

Just a few hours ago I gave ChatGPT my window sticker and the installation manual for a new suspension setup. I asked for new hardware that would typically be replaced during this install, like torque-to-yield bolts and fasteners. I also asked for new oil filters. I got a comprehensive grid of the exact part numbers needed in a nice dense table. sol 5.6 high is my daily driver.

You'll be re-buying half those parts when the part numbers come back incorrect, lol

Re: Show HN: I made a Raspberry with Qwen my local car AI

#45

Post by whalesalad »

ssl-3 wrote: post #34
whalesalad wrote: post #26

Earlier quoted context omitted.

Just a few hours ago I gave ChatGPT my window sticker and the installation manual for a new suspension setup. I asked for new hardware that would typically be replaced during this install, like torque-to-yield bolts and fasteners. I also asked for new oil filters. I got a comprehensive grid of the exact part numbers needed in a nice dense table. sol 5.6 high is my daily driver.

> sol 5.6 high is my daily driver. Mine, too. Did you fact-check the output? I've found the bot to be particularly bad at stuff like producing accurate lists of parts to replace during automotive projects.

So far so good, hasn’t failed me yet. It’s done a stellar job chasing down parts for my cub cadet lawn mower too. Sorted out mid year model revisions and everything. I just gave it the sticker under the seat.

Re: Show HN: I made a Raspberry with Qwen my local car AI

#46

Post by voidUpdate »

hypfer wrote: post #10

What is the LLM doing there? Why does it need to be hooked up to the car for you to ask it which type of engine oil the manual recommends? What is the point?

People don't want to ask google, they just want to ask their plagiarism machine instead and be fed some answers directly, correctness be damned

Re: Show HN: I made a Raspberry with Qwen my local car AI

#47

Post by fedeb95 »

I think you should provide better use case scenarios that make clear why this project is useful.

I can already change AC and lock doors with two buttons, why it should be better to do it by voice? Pressing those buttons is way faster.

I guess the manual RAG is useful, what I am saying is that use cases aren't clear from your post or README. As it is, one reads it as "cool, LLM in a car", and skips it.

Re: Show HN: I made a Raspberry with Qwen my local car AI

#48

Post by embedding-shape »

alexandra_au wrote: post #27
ehnto wrote: post #14

Fair warning, I have found local models and frontier models to be very bad at the specifics when it comes to cars. Small differences like month and year model can impact oil capacity, oil weight and things like that, the details that matter quite a bit. I found frontier models couldn't get things like what engine was in a 1994 Nissan Skyline, one of the more infamous and talked about cars on internet forums for decad…

It's nothing that tool calling/feeding it the correct information can't solve

Even so, in this case, author is using UD-Q3_K_S dynamic weights for Qwen3.6-35B-A3B, it will be dumb. Even the BF16 weights do stupid stuff like missing to confirm all parameters are defined when doing "rm -rf directory/$id", so it ends up deleting more than expected, I can't imagine the Q3 are actually useful for anything serious, even with tool calling or what not.

Re: Show HN: I made a Raspberry with Qwen my local car AI

#49

Post by ssl-3 »

whalesalad wrote: post #45
ssl-3 wrote: post #34

Earlier quoted context omitted.

> sol 5.6 high is my daily driver. Mine, too. Did you fact-check the output? I've found the bot to be particularly bad at stuff like producing accurate lists of parts to replace during automotive projects.

So far so good, hasn’t failed me yet. It’s done a stellar job chasing down parts for my cub cadet lawn mower too. Sorted out mid year model revisions and everything. I just gave it the sticker under the seat.

It makes stuff up about my car all the time, even when provided with factory and/or aftermarket service manuals to peruse in a custom GPT.

That car is a ridiculously-common Honda Odyssey with an engine that is even more-common.

I do sincerely wish you good luck with your suspension project.

Post reply on HN