CarWatch

AI

in-car voice assistant

SHOW HN2026

146points
68comments
#446of 4,366 in 2026
Top 11%of 2026 by points

How HN took it

CuriousMostly questions and neutral comments

3 positive, 17 neutral or asking, 0 mixed, 14 critical, out of 34 comments about the project. Thread score -0.29.

Idea: 2 for, 3 againstPerformance: 0 for, 4 againstDocs: 0 for, 4 againstPricing: 0 for, 2 againstExecution: 0 for, 1 against

The thread, comment by comment

Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.

positive neutral or mixed critical about another commenter or something else the maker

What HN said

What people liked

  • Impressive local model performance on a Pi

    From 1 comment
  • Maker reports low hallucination rate with RAG on manual

    From 1 comment
    • I've been very impressed by it's intelligence and lack of hallucinations. The dynamic Q3 is a good balance between accuracy and size keeping the 35B just below 16 GB. It is not…
      petruspennanen on HN

Objections

  • Model choice too slow and too heavy for Pi memory bandwidth

    From 1 comment
    • The issue is not RAM size. It's memory bandwidth! The 12B and 31B models will be useless on a Pi 5; maybe the 12B can be persuaded to run, but it may not manage more than one…
      dofm on HN
  • Unclear use cases beyond what buttons already do

    From 2 comments
    • 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…
      fedeb95 on HN
    • At one point, every machine on earth is going to be its own agent, asking and answering questions and expressing concerns. Its like a good example of that, but I think the…
      sshussain270 on HN
  • Local models unreliable on specific car details

    From 2 comments
    • 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…
      ehnto on HN
    • 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…
      ssl-3 on HN
  • Readme includes unverified claims and reads as AI-written

    From 3 comments
    • I'm currently integrating one for simple diagnostic readouts to integrated small touchscreen. The main goal being a retro looking display that mainly dumps ODB data/monitors, but…
      Reubachi on HN
    • From readme: """ Unverified against the real car — it will confirm or refute itself on the next drive """ Looks like a ton of this is aspirational. For your project -- do you…
      VTimofeenko on HN
    • I scanned this README looking for the part written by a human and gave up when I realized there wasn't one. the Mermaid diagram doesn't even render.
      tessierashpool on HN

Requests

  • Clearer use cases with status indicators

    From 1 comment
    • Thanks point taken, will add clear use cases with proven / in testing / planned status indicators!
      petruspennanen on HN
  • Support for more car brands via cloud integrations

    From 1 comment
    • Yes Qwen runs local. Manufacturer cloud workw via existing integrations (they have many) in Home Assistant. The Pi makes a secure tunnel to my home assistant running on a Mac…
      petruspennanen on HN
  • Try a smaller, faster reasoning model

    From 2 comments
    • The issue is not RAM size. It's memory bandwidth! The 12B and 31B models will be useless on a Pi 5; maybe the 12B can be persuaded to run, but it may not manage more than one…
      dofm on HN
    • Hmm could try Ornith - wouldn't mind if answers came a bit faster. Probably hard to reach Qwens intelligence level though.
      petruspennanen on HN

Questions

  • How does it handle trim/year ambiguity and show sources?

    From 2 comments
    • I’d be most interested in how it handles uncertainty when the answer depends on trim/year or service history. For a car assistant, a useful default might be “I found the relevant…
      jiangriver66 on HN
    • It refers to the manual page, that's really all you can do in that case especially offline.
      petruspennanen on HN
  • What hardware is needed for OBD data?

    From 2 comments
    • What's the hardware situation to get OBD data?
      yjftsjthsd-h on HN
    • Any standard OBD-II ELM32 will work, they are like $15.. Mine is a Vgate iCar Pro over bluetooth. A USB ELM327 v1.5 also works
      petruspennanen on HN

Alternatives named

  • Freematics One+ for OBD and GPS

    From 1 comment
    • I have no idea on OP, but as far as a waypointer, have been in the area of building bespoke automotive telemetry solutions for a while now (including reversing some existing…
      rpcope1 on HN
  • Perplexity for fact-checking

    From 1 comment
    • For prompts that needs fact-checking, I like these days to use Perplexity directly instead these days. It's way faster than the default websearch tool + give a link to the…
      ygouzerh on HN
  • Pitstop app

    From 1 comment
    • I will shamelessly plug https://pitstop.app. I've been working on this for years and I work on/race cars regularly. I wouldn't fully trust LLMs with this :p BUT this project is…
      Robdel12 on HN

Category, keywords, summaries and labels on this page were made by AI (Thread Reader v2) and not checked by hand. Each point links to the comments it came from.

Add a badge to your READMEShown on HackerShow
[![Shown on HackerShow](https://hackershow.org/badge.svg)](https://hackershow.org/show/49435675)