Literally just last night I have Claude Code the following prompt, verbatim:
"Whenever I launch Kodi on my Chromecast 4k, it crashes. I think this is
related to a plugin or skin. It goes away for a bit if I clear cache but
will eventually come back. Can you connect to the device via
adb (I've run adb connect already), and debug exactly where it's crashing?
Once you've done that, propose a solution. If this requires downloading,
fixing, rebuilding and then uploading the broken extension via adb, don't be
shy. I should have Android dev tools (Gradle etc.) on this Mac."
Lo and behold, without human intervention, it pinpointed the crash, downloaded the Kodi source, patched out a bug that had existed since 2016, recompiled it, signed it, then pushed it to my Chromecast all while carefully making sure to keep all my settings intact.
Got it to make a PR too (which is as of this moment unpublished; going to test more over the coming weeks).
I know this isn't apples to apples, but given that I can't get Copilot or other tools to view a simple profile page on LinkedIn makes me curious/skeptical how this would work in this depth. I'm sure it's possible but I'm curious what the skills and toolchains involved were for you to get all that to work.
on frontend-design:frontend-design · plugin · ~90 tok · locked by plugin
on agents-sdk · user · ~150 tok
on cloudflare · user · ~130 tok
on cloudflare-email-service · user · ~180 tok
on durable-objects · user · ~130 tok
on find-docs · user · ~300 tok
on find-skills · user · ~110 tok
on sandbox-sdk · user · ~120 tok
on stage-chapters · user · ~40 tok
on web-perf · user · ~150 tok
on workers-best-practices · user · ~130 tok
on wrangler · user · ~120 tok
But yeah, this is more or less vanilla Claude Code - at least, nothing related to Android or adb there.
It's that good now. A few days ago I asked it to SSH into my Ubuntu box and investigate a hang. It didn't solve the problem fully autonomously like this time but did tell me a whole lot things it wasn't, and hinted at a faulty driver. We went back and forth a bit, it set up a watchdog and taught me how to update the kernel without updating Ubuntu itself, and the server has been rock solid for the past 3-4 days now.
Also, if you're curious, full log for the Kodi issue:
I did prompt it a little bit more today in order to get something more production-ready (the original solution kept regenerating the cache on boot, rather than fixing it permanently), but you can see the whole original autonomously-generated solution in the logs. It's insane, seriously.
Claude Code (or Codex, or OpenCode, or Pi, or Amp — whatever) can do this out of the box without any skills or special tools. The most important thing for making results like this easier to achieve (in any harness) is using the best current models. Right now that's Opus 4.8 and GPT-5.5.
To expand on another answer, it’s all about the harness. Different harnesses (Claude Code or Cowork, Hermes, OpenCode, Pi, etc.) offer different default tools, system prompts, and ultimately approaches. (IME the corporate CoPilot app is terrible - basically a chat interface.)
I’m currently using Hermes for local LLMs - seems pretty good so far.
LinkedIn in particular is quite aggressively blocking any automated attempts to read or navigate through it.
I post quite a lot there and wanted to have a copy of my posts on my blog[0] to preserve them. For a few months I was able to use a headless browser + claude code, then LI wised up and started logging it out, so I had to use a regular Chrome, log in manually and then tell the LLM to take over and slowly go through my feed.
If you're accessing sites which are not actively blocking bots, or - gasp - have an API, it's much better.
So I'm scrolling through this Ask HN and this is now the 3rd similar problem. Would you mind adding more details as well as the patch? Perhaps as a gist if it's unfinished?
It seems to be a quite common problem. Are you sure it was the rube goldberg fix and not a more mundane solution? Such as pulling in someone's fork from GitHub or just clearing the cache on a loop?
And yes, it correctly diagnosed the problem - I confirmed this morning. The cache had been partially deleted (exactly like it said) and the patched version of the software automatically detected this and rebuilt the cache rather than crashing. This was using the initial version of the patch from commit 1 of the PR.
I then talked with Claude a bit to come up with a less hacky solution that doesn't require constant cache rebuilding, and it suggested writing the "cache" to no_backup, bypassing the cache trimmer. However, this required rebuilding the .so via NDK, so it spun up a full VM in multipass, installed all the tools in there to build the fully patched APK, and built it (the VM was my suggestion, it was about to just brew install everything and mess with my local dev environment).
I think the key takeaway from this experience (and a few others recently) is that Claude Code works much, much better when you explicitly instruct it to test against real data.
Had I simply described the issue and asked it to think up a solution it likely would have just navel-gazed and then come up with a wrong solution. But by pointing it at a real working environment and actively encouraging it to get its hands dirty, it found the actual solution rapidly - in spite of the fact that I gave it wrong information twice.
I realize from your perspective this may seem still a very convincing example in the sense of it works.
A non-programmatic solution might have been possible though:
> It's likely your thumbnail cache. That's typically the biggest piece stored locally (you also have the database). You can clear the cache (short term fix) or move it to another drive (long term fix).
> Also recommend not downloading actor thumbnails. Lot of extra images.
That's amazing, as someone who struggles to find something useful to do with LLMs. How long does this take, several minutes or more? Do you need a paid version of Claude Code for this?
It sat there for about half an hour working out the problem, step by step, before asking me for the preferred solution. At one point, it was trying to decompile the .APK, so I interrupted it and reminded it that Kodi was open source - it was welcome to clone from GitHub.
The only other feedback I gave it mid-process was wrong (I said that the crash probably wasn't caused by cache trimming, it ran some additional tests to confirm that its hunch about cache trimming was right).
This was with the paid version of Claude Code (I don't think they offer a free version at all; that's a Codex thing). The $20 version is as smart as the $200 one, but once you work out it can do stuff like this you'll quickly burn the $20 token limit. :)
The other thing that helps is a CLAUDE.md file - authored of course by Claude itself.
Mine's here: https://github.com/EspoTek/.claude/blob/master/CLAUDE.md
A lot of it is probably domain-specific for the stuff I do, but the "Working with unfamiliar data or systems" section is bloody gold! Stopped the bullshit completely!
"Whenever I launch Kodi on my Chromecast 4k, it crashes. I think this is related to a plugin or skin. It goes away for a bit if I clear cache but will eventually come back. Can you connect to the device via adb (I've run adb connect already), and debug exactly where it's crashing? Once you've done that, propose a solution. If this requires downloading, fixing, rebuilding and then uploading the broken extension via adb, don't be shy. I should have Android dev tools (Gradle etc.) on this Mac."
Lo and behold, without human intervention, it pinpointed the crash, downloaded the Kodi source, patched out a bug that had existed since 2016, recompiled it, signed it, then pushed it to my Chromecast all while carefully making sure to keep all my settings intact.
Got it to make a PR too (which is as of this moment unpublished; going to test more over the coming weeks).