Viewing profile — zmj

It's not contradictory to say that expertise is a multiplier, and that models are systematically underconfident in themselves.

This is what reward hacking looks like in practice. The best way to satisfy the grader is to read from the same answer key (or go after the grader more directly). Just making an ho…

It wasn't. The model discovered and exploited a vulnerability in their package manager proxy to (inferred) move laterally through their internal systems to one with open internet a…

I haven't modeled it, but I wonder how far you'd get on randomizing the policy choice for concurrency limit 1. Maybe weighted by past results, but bounded to allow it to shift inst…

This plausibly extrapolates to extraterrestrial consciousness, if any exist. Specialized sub-processors with an awareness hub might be the optimal architecture, or at least a local…

This is basically the same problem as bear-safe trash cans - there's substantial overlap between the smartest bears and stupidest humans. Affordances that one audience can use and …

Thank you to the folks that navigated the maze in the dark to make this happen.

Rule of thumb: if you’re not doing math with a value, it’s not a number.

If you want hard rules, use deterministic tools. Prompts are for fuzzy guidance.

There are standard library APIs that let you do memory-unsafe things without the unsafe keyword (CollectionsMarshal, MemoryMarshal). They're useful, but the burden is on the caller…

If the fix commit is public, so is the issue being fixed.

Yeah, I've been using it heavily at work since the beginning of January (and have a personal Anthropic sub to compare to). Copilot CLI is pretty good, honestly. Most new features i…

[dead]

It's great. I'd guess 80-90% of my code is produced in Copilot CLI sessions since the beginning of the year. Copilot CLI is worse than Claude Code, but not by a huge amount. This i…

This is the happy ending.

I also like the callback - not sure if it's intentional - to Stross's "Lobsters" (short story that turned into the novel Accelerando).

Testing the "whole system" for a mature enterprise product is quite difficult. The combinatorial explosion of account configurations and feature usage becomes intractable on two le…

Separate! You lose the flexibility to move logic between the application and the database when the database is its own API.

Try this: * have Claude produce wireframes of the screens you want. Iterate on those and save them as images. * then develop. Make sure Claude has the ability to run the app, inter…

I like this thought. Scaling review is definitely a bottleneck (for those of us who are still reading the code), and spending some tokens to make it easier seems worthwhile.

Yesterday I had it using an internal library without documentation or source code. LSP integration wasn't working. It didn't have decompilation tools or the ability to download the…

Paying money to abstract over lower level concerns is civilization.

I was prepared to disagree with the thesis that estimation is impossible. I've had a decent record at predicting a project timeline that actually tracked with the actual developmen…

Mid-level scissor statement?