181–190 of 211 posts
Earlier quoted context omitted.
I want to try one to be a bit of a personal coach. Remind me to do things and check in on goals. The memory / schedule / chat thing is enough and it wont need emails or anything more dangerous.
As someone who went down so many "productivity rabbit holes" I think this is a great idea.
> OpenClaw has nearly half a million lines of code, 53 config files, and over 70 dependencies. This breaks the basic premise of open source security. Chromium has 35+ million lines, but you trust Google’s review processes. Most open source projects work the other way: they stay small enough that many eyes can actually review them. Nobody has reviewed OpenClaw’s 400,000 lines. This reminds me of a very common thing po…
Respectfully, it feels like your position requires a very low, if not brain-dead level of incompetence on the part of LLM users, in order for your conclusion to be correct. My personal anecdote: I used an LLM recently to basically vibe code a password manager. Now, I’ve been a software engineer for 20 years. I’m very familiar with the process of code review and how to dive in to someone else’s code and get a feel for…
How can you say that when all these models are externally sourced by companies that actively make a loss per token? When they finally need to make a profit, how can we be sure these models as well as their owners will remain as reliable and not enshittified? Anthropic has been blacklisted in the last 24 hours so its a turbulent industry to say the least
Earlier quoted context omitted.
Author and creator of NanoClaw here. I did my best to communicate this but I guess it was still missed: NanoClaw is not software that you should run out of the box. It is designed as a sort of framework that gives a solid foundation for you to build your own custom version. The idea is not that you toggle on a bunch of features and run it. You should customize, review, and make sure that the code does what you want.…
So, nanoclaw requires agents to code extensions on the fly to get to feature parity with openclaw… and you're celebrating nanoclaw having fewer LOC. How's the code smell after nanoclaw gets to feature parity?
A question I've been asking myself and which I honestly want to put out there - and I apologize in advance, because you will see me repeat it in other threads, out of genuine curiosity: Does your life have so much friction that you need a digital agent to act on your behalf? Some of the use cases I saw on the OpenClaw website, like "checking me into a flight", are non-issues for me. I work in business automation, but…
That said, old beliefs should be challenged by new technological capabilities!
If LLM based automation is (a) less fragile and (b) quicker to develop, then that bar should be lowered.
Earlier quoted context omitted.
Respectfully, it feels like your position requires a very low, if not brain-dead level of incompetence on the part of LLM users, in order for your conclusion to be correct. My personal anecdote: I used an LLM recently to basically vibe code a password manager. Now, I’ve been a software engineer for 20 years. I’m very familiar with the process of code review and how to dive in to someone else’s code and get a feel for…
>this tech is here to stay How can you say that when all these models are externally sourced by companies that actively make a loss per token? When they finally need to make a profit, how can we be sure these models as well as their owners will remain as reliable and not enshittified? Anthropic has been blacklisted in the last 24 hours so its a turbulent industry to say the least
I run Claude Code with 84 hooks, and the one I trust most is a macOS Seatbelt (sandbox-exec) wrapper on every Bash tool call. It's about 100 lines of Seatbelt profile that denies read/write to ~/.ssh, ~/.gnupg, ~/.aws, any .env file, and a credentials file I keep. The hook fires on PreToolUse:Bash, so every shell command the agent runs goes through sandbox-exec automatically.
The key design choice: Seatbelt operates at the kernel level. The agent can't bypass it by spawning subprocesses, piping through curl, or any other shell trick — the deny rules apply to the entire process tree. Containers give you this too, but the overhead is absurd for a CLI tool you invoke 50 times a day. Seatbelt adds ~2ms of latency.
I built it with a dry_run mode (logs violations but doesn't block) and ran it for a week before enforcing. 31 tests verify the sandbox catches attempts to read blocked paths, write to them, and that legitimate operations (git, python, file editing in the project directory) pass through cleanly.
The paths to block are in a config file, so it's auditable — you can diff it in code review. And it's composable with other layers: I also run a session drift detector that flags when the agent wanders off-task (cosine similarity against the original prompt embedding, checked every 25 tool calls).
None of this solves prompt injection fundamentally, but "the agent physically cannot read my SSH keys regardless of what it's been tricked into doing" is a meaningful property.
Yeah, but the world rewarded this by making it the fastest growing github project. The author gets on the podcasts, gets the high profile jobs from big tech. I'm more encouraged to do things this way than being security minded about all this.
And there's no accountability to this at all. If an agent leaks private data, the user is to blame and not the author. If Google bans your services for using api keys incorrectly, we cast the bad eye towards Google and not the maintainer than enabled and approved it.
There's just so much incentive for for "not reading code" and not developing secure code that is just going to get worse over time. This is the hype and the type of engineering that we all allow either by agreeing or by staying silent.
I agree with the author, but the world works off a different set of principles than what we're used to. I just see the world blindly trusting agents more.
Earlier quoted context omitted.
This whole reply, and every other "anecdote" reply is more worthless than the pixels its printed on, without a link to your "actually did a good job" password manager. (wow funny how these vibe code apps always are copies of something theres many open source versions of already)
Ugh, you made me spend the 20 minutes it takes to spin up a new github account to share this (my existing one uses my real name and I don't really want to doxx myself that much. Not that it's a huge deal, my real identity and the "ninkendo" handle have been intertwined a lot in the past.) https://github.com/ninkendo84/kenpass I'm not saying it's perfect, there's some things I would've done differently in the code. It…
A question I've been asking myself and which I honestly want to put out there - and I apologize in advance, because you will see me repeat it in other threads, out of genuine curiosity: Does your life have so much friction that you need a digital agent to act on your behalf? Some of the use cases I saw on the OpenClaw website, like "checking me into a flight", are non-issues for me. I work in business automation, but…
It is not about removing friction, it is about convincing that friction existed in a first place