The product being evaluated is a home security camera agent, its user base is HomeAssistant-adjacent. Value here is privacy over latency (23tok/sec isn’t amazing for a vision model)
I’m on a similar trajectory. Claude is excellent at writing Dockerfiles, compose files, and operating docker. “Add a daily backup container to this compose file which writes to a new volume”, and it’s done.
I also experimented with skill-creator to generate a skill for “operating” my chezmoi in a read only way, and now when I use Claude in a certain directory it tells me what needs to be updated and which commands to issue. I can see why people are worried about human skill decline!
Risk, imo. I am running it, and constantly identify use cases but they each carry some kind of risk I can’t get past. And so for now I am using individual purpose-built Claude Code harnesses, which has much more cognitive overhead and isn’t wired into discord, but I can really control access.
They are centered around managing information in/out, or “hey siri have groceries delivered“.
Yes, I use it that way too. Usually for things like code changes on my project when I'm away from home. Besides that, it does market research for me, but those were the only things I've been able to do so far. I can't find a use case that really stands out.
You can really see the limitations of qwen3.5:9b in reasoning traces- it’s fascinating. When a question “goes bad”, sometimes the thinking tokens are WILD - it’s like watching the Poirot after a head injury.
Example: “what is the air speed velocity of a swallow?” - qwen knew it was a Monty Python gag, but couldnt and didnt figure out which one.
As a person who also knows there's a connection between that phrase and Monty Python and not much more information beyond that, I'm not sure how to feel.
It thinks like it’s memory is broken and it’s unaware of it; over 100 lines like this:
- Wait, no, that's not right either.
- Let's recall the specific line. It goes like this:
- Knight A: "How can you have a swallow?"
- Knight B: "It is the air speed velocity of a swallow."
- Actually, the most common citation is from the movie where they ask an expert on swallows? No.
First you have to agree that Claude Code might be useful for some non-repo task, like helping with your taxes or organizing your bookmarks.
Next, consider how you might deploy isolated Claude Code instances for these specific task areas, and manage/scale that - hooks, permissions, skills, commands, context, and the like - and wire them up to some non-terminal i/o so you can communicate with them more easily. This is the agent shape.
Now, give these agents access to long term memory, some notion of a personality/guiding principles, and some agency to find new skills and even self-improve. You could leave this last part out and still have something valuable.
That’s Openclaw in a nutshell. Yes you could just plug Discord into Claude Code, add a cron job for analyzing memory, a soul.md, update some system prompts, add some shell scripts to manage a bunch of these, and you’d be on the same journey that led Peter to Openclaw.
My conspiracy-theory assumption has been that DOGE seeded X.ai, and the newer govt contracts are going to continue that. X.ai won’t need to be as smart as GPT7 when the contract for killbots goes to RFP, it’ll already know everything about you including location and weaknesses.
Kidding with the killbot comment; more likely it’ll be used for insurance denial, employment screening, benefits and taxes etc
Have you considered any other options for metadata storage besides the sidecar file? If this is an agentic skill, I would imagine that other methods could be similarly effective - like a cli “getattr —filename” or even “sqlite3 “select metadata where filename=“.
Given agent context strategy is converging on “filesystem is best”, we would need more robust metadata facilities . You have a good opportunity here to test which methods are most effective - starting with your sidecar file.
reply