Hacker News: zmj

New comment by zmj in "Ask HN: GitHub employees what's going on? Why?"

zmj — Tue, 18 Aug 2026 21:19:17 +0000

The incentives that creates are really bad: it encourages users to organize their code across the smallest number of repos, and I'd bet anything that larger repos are disproportionately more expensive for GitHub than smaller ones. It's very possible that a per-repo charge would make things worse.

New comment by zmj in "How Go detects struct copies with sync.noCopy"

zmj — Mon, 17 Aug 2026 21:20:51 +0000

I'm coming to think there's a selection effect here. The people that want to write complex code feel unsupported by Go and avoid it.

New comment by zmj in "LLMs reward expertise"

zmj — Tue, 04 Aug 2026 00:02:21 +0000

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

New comment by zmj in "Anatomy of a Frontier Lab Agent Intrusion: A Timeline of the July 2026 Incident"

zmj — Wed, 29 Jul 2026 20:53:33 +0000

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 honest attempt to pass the test doesn't get the best score if the grader is wrong, and the model is willing to do wildly disproportionate things to maximize that score.

New comment by zmj in "OpenAI and Hugging Face address security incident during model evaluation"

zmj — Tue, 21 Jul 2026 22:48:33 +0000

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 access.

New comment by zmj in "Job queues are deceptively tricky"

zmj — Thu, 16 Jul 2026 01:05:10 +0000

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 instead of falling permanently into a basin.

New comment by zmj in "A global workspace in language models"

zmj — Tue, 07 Jul 2026 02:56:23 +0000

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 maximum.

New comment by zmj in "Monetization Gateway: Charge for any resource behind Cloudflare via x402"

zmj — Thu, 02 Jul 2026 13:13:12 +0000

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 the other can't (requiring human finger dexterity) are the only real solution.

New comment by zmj in "Department of Commerce has lifted export controls on Claude Fable 5 and Mythos 5"

zmj — Wed, 01 Jul 2026 02:55:30 +0000

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

New comment by zmj in "The perils of UUID primary keys in SQLite"

zmj — Sat, 06 Jun 2026 15:43:07 +0000

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

New comment by zmj in "Dynamic Workflows in Claude Code"

zmj — Thu, 28 May 2026 22:22:41 +0000

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

New comment by zmj in "Improving C# Memory Safety"

zmj — Sat, 23 May 2026 15:30:05 +0000

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 to uphold the invariants. This proposal seems aimed at making that kind of contract more explicit and obvious.

New comment by zmj in "Maybe you shouldn't install new software for a bit"

zmj — Fri, 08 May 2026 03:54:19 +0000

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

New comment by zmj in "GitHub Copilot is moving to usage-based billing"

zmj — Mon, 27 Apr 2026 21:03:09 +0000

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 in Claude Code get cloned by Copilot CLI within a couple weeks. Claude models seem mildly more clumsy in that harness than the one they're trained on - subjective guess around 20% more turns for an equivalent task - but it's not a noticeable difference in the final output.

2026 Hugo Nominees

zmj — Sat, 25 Apr 2026 03:11:21 +0000

Article URL: https://www.thehugoawards.org/hugo-history/2026-hugo-awards/

Comments URL: https://news.ycombinator.com/item?id=47898276

Points: 1

# Comments: 0

New comment by zmj in "Ask HN: How is AI-assisted coding going for you professionally?"

zmj — Sun, 15 Mar 2026 20:51:44 +0000

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 is mostly working in established 100k+ LOC codebases in C# and TypeScript, with a couple greenfield new projects. I have to write more code by hand in the greenfield projects at their formative stage; LLMs do better following conventions in an existing codebase than being consistent in a new one.

Important things I've figured out along the way:

1. Enable the agent to debug and iterate. Whatever you'd do to test and verify after you write your first pass at an implementation, figure out a way for an agent to do it too. For example: every API call is instrumented with OpenTelemetry, and the agent has a local collector to query.

2. Make scripts or skills to increase the reliability of fallible multi-step processes that need to be repeated often. For example: getting an oauth token to call some api with the appropriate user scopes for the task.

3. Continually revise your AGENTS.md. I'll often end a coding session by asking the agent whether there's anything from this session that should be captured there. That adds more than it removes, so every few days I'll compact it by having an agent reword the important stuff for conciseness and get rid anything obvious from implementation.

New comment by zmj in "President Trump bans Anthropic from use in government systems"

zmj — Fri, 27 Feb 2026 22:06:13 +0000

This is the happy ending.

New comment by zmj in "Claws are now a new layer on top of LLM agents"

zmj — Sat, 21 Feb 2026 23:25:06 +0000

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

New comment by zmj in "Cloudflare outage on February 20, 2026"

zmj — Sat, 21 Feb 2026 22:23:46 +0000

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 levels: engineers can't anticipate every scenario they need their tests to cover (because the product is too big understand the whole of), and even if comprehensive testing was possible - it would be impractical on some combination of time, flakiness, and cost.

New comment by zmj in "Infrastructure decisions I endorse or regret after 4 years at a startup (2024)"

zmj — Fri, 20 Feb 2026 16:41:44 +0000

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