I've got a gitea instance and a systemd timer polling for issues assigned to my bot. The systemd timer clones the repo etc and spawns the agent in a restricted environment where it has a private localhost (enforced by systemd), and then I set HTTP_PROXY to an inner proxy that connects to an outer proxy over a unix socket. The outer proxy enforces an allowlist and injects credentials. The agent doesn't have access to any credentials inside its sandbox.
For the agent I was using `claude -p` with a pro subscription, but they've been treating their paying subscribers like they're on a free trial (they're subsidizing it so heavily it might as well be). So now I'm using an ollama pro subscription and a homebuilt agent with a bash tool and a str_replace tool. It gets on just fine with only those two
> If you wrote a function that takes a PRNG and generates a random object, you already have a function capable of enumerating all objects.
Something often forgotten here: if your PRNG only takes e.g. a 32-bit seed, you can generate at most 2^32 unique objects. Which you might chew through in seconds of fuzzing.
Edit: this is addressed later in the article/in a reference where they talk about using an exhaustive implementation of a PRNG interface. Neat!
I actually started a collection of annoying bugs I’ve seen in the wild. I give the llm the buggy implementation and ask it to write a test that catches it. So far not even a frontier model (Claude Sonnet) can do it, even though they can find and fix the bug itself.
For the agent I was using `claude -p` with a pro subscription, but they've been treating their paying subscribers like they're on a free trial (they're subsidizing it so heavily it might as well be). So now I'm using an ollama pro subscription and a homebuilt agent with a bash tool and a str_replace tool. It gets on just fine with only those two