navels
Joined 14 years ago
Karma
237
Submissions
76
Member since
Dec 12
Recent submissions
Comment · 2 months ago
Comment · 2 months ago
Thanks!
Comment · 2 months ago
I've built an orchestrator that solves some of the issues you ran into (although it doesn't do anything about cheating): https://navels.dev/blog/neal/. Features:
- lets you configure different models for planner, coder, and reviewer roles. (e.g., using Claude as an adversarial reviewer against Codex)
- breaks your plan up into reasonable-sized chunks of work with clearly defined success criteria
- runs each chunk of work through a coder / read-only reviewer loop. Once both agents are satisfied, neal moves on to the next chunk. Once everything is complete there is a final pass through the coder / reviewer loop to ensure the implementation satisfies the entire plan.
- resets the coder's context with each chunk of work to prevent context drift, leaving the reviewer's context long-running.
Comment · 2 months ago
I've been using this CC hook with decent results: https://github.com/gvzdv/claudish-to-english
It uses a local LLM to translate Claude's output.
Comment · 2 months ago
The migration was not a single, long run of neal (because I was developing/tweaking neal along the way). However I have used it for large-ish implementations and haven't noticed any issues with the reviewer drifting. It is re-prompted each review turn with its adversarial review instructions plus a summary of the run state (completed scopes, open findings, etc). Also, the final review is executed with a fresh context.
Comment · 4 months ago
lol how many of these things are there. I've been using https://github.com/f-is-h/usage4claude which includes Codex usage (I use Claude and Codex).
Comment · 9 months ago
Other activites such as the sublime pursuit of truth and beauty . . . aka mathematics ;-)
Comment · 1 year ago
The rule is based on the symbol, not the color. Ie, there is no green or blue rule.
Comment · 1 year ago
same parent had said "It's crazy that a language that prioritizes security so highly in it's design itself is only compiled through such insecure methods."
Comment · 1 year ago
why not?
Comment · 2 years ago
How weird, tteck's site is great and what is this nonsense about security.
Comment · 2 years ago
I'm confused about whether/how this is related to https://github.com/tteck/Proxmox/
Thanks for the feedback. I've made a couple of updates:
- Starting with 0.4.0, the reviewer gets the diff of the earlier chunk for any file the current chunk touches again. Also, if a new chunk weakens or removes a test or assertion from an earlier chunk, the reviewer will block it unless the plan says to do so.
- About read-only: The reviewer's tools were already limited by the SDK (no shell or write tools). However, it was still finding MCP servers from my Claude config. I have now blocked those. The docs now explain what is enforced by the system and what is just a prompt instruction.