Hacker News: breckenedge

New comment by breckenedge in "How to Build Wealth as a Career Person"

breckenedge — Sun, 11 Oct 2026 18:57:56 +0000

Understand when you’re in a meritocracy versus a plutocracy. Outshining the favorite son can be harmful.

New comment by breckenedge in "Order of the Sinking Star"

breckenedge — Thu, 08 Oct 2026 17:31:16 +0000

Before we were married, my future wife and I played The Witness together on my iPad. Fond memories, hope this gets a mobile release too.

New comment by breckenedge in "Ask HN: Is the Future of IDEs Bleak?"

breckenedge — Wed, 07 Oct 2026 23:11:32 +0000

Yea. I haven’t opened VS code in I don’t know how long. Among other things, I just shipped a full mobile app for Android and iOS and never had to touch XCode or Android Studio.

New comment by breckenedge in "Factorio that you can touch"

breckenedge — Fri, 25 Sep 2026 16:16:28 +0000

The factory must grow.

New comment by breckenedge in "Claude Opus 5.5 Intelligence, Performance and Price Analysis (Max)"

breckenedge — Fri, 25 Sep 2026 00:09:22 +0000

Just about 90 PRs in that dataset to review.

New comment by breckenedge in "Claude Opus 5.5 Intelligence, Performance and Price Analysis (Max)"

breckenedge — Tue, 22 Sep 2026 23:03:40 +0000

This is all code review runs via OpenRouter with a Pi harness, and it’s totally possible there are shenanigans going on elsewhere.

Yesterday, I ran an identical bug identification dataset from two weeks ago, saw a 50% drop from a few weeks ago, putting Sol on the same level as Luna. Sol had been finding 40-50 bugs per set, then dropped to 25, matching Luna’s performance. Not enough to establish a pattern, but enough to raise eyebrows.

Our review workflow is public if you want to peruse it, dataset isn’t. The process isn’t really stabilized yet either as I have to balance running this against limited budgets.

https://github.com/BiggerPockets/.github/blob/main/.github/w...

New comment by breckenedge in "Claude Opus 5.5 Intelligence, Performance and Price Analysis (Max)"

breckenedge — Tue, 22 Sep 2026 17:33:27 +0000

Do these evaluations get re run a few weeks after launch? I started doing that yesterday for our internal dataset and found Sol’s performance had regressed to be equal to Luna’s. Granted this was one run, but something I’m becoming more concerned about, the model providers want to quickly prove they’re the best, people switch to them, then they pull the rug.

New comment by breckenedge in "Ask HN: How do you manage skills files?"

breckenedge — Thu, 10 Sep 2026 18:32:42 +0000

Yea I definitely keep engineering skills and org skills separate.

New comment by breckenedge in "Ask HN: How do you manage skills files?"

breckenedge — Mon, 07 Sep 2026 12:32:46 +0000

My approach is different. Skills I write mostly use Python to save on the agent needing to run its own loops.

I use these loops to monitor the CI build and PR approvals rather than having the agent poll, and even Opus gets the commands wrong enough to make it worth it.

Last week I wired up a skill for the agent to share screenshots in PRs via specific S3 buckets and AWS CLIs. Again, the agents guess at the right commands often enough to make it worth being explicit.

Sure these could have gone in CLAUDE.md, but not every agent needs the context.

And at the company level, I can push skills to everyone’s Claude via the Teams function, they don’t need to edit configs or even know what a skill is.

New comment by breckenedge in "Do teams still use scrum and sprints?"

breckenedge — Mon, 24 Aug 2026 16:53:17 +0000

Those terms became way too ambiguous to actually mean anything. Every team does it different.

New comment by breckenedge in "Ask HN: Will AI trigger mass IP protectionism in software?"

breckenedge — Sun, 23 Aug 2026 13:34:45 +0000

Yes, and not just code. It’ll be Gnosticism all over again.

New comment by breckenedge in "Ask HN: What AI automations have you kept running in production?"

breckenedge — Thu, 20 Aug 2026 12:13:27 +0000

HN reply bot

New comment by breckenedge in "The Ploopy A+ Trackball Is Here"

breckenedge — Sat, 15 Aug 2026 02:25:50 +0000

I get it doesn’t appeal to you. Why do you think it shouldn’t appeal to anyone?

New comment by breckenedge in "Waymo – Dallas Open to All"

breckenedge — Tue, 04 Aug 2026 19:47:58 +0000

Service area is still miniscule.

New comment by breckenedge in "AI PR reviewer is looking at the diff, not the intent"

breckenedge — Mon, 27 Jul 2026 12:13:58 +0000

Yes, I fetch Jira tickets and epics via API call in the reviewer’s action. Both Codex and Claude can then reference it. Source is public here:

https://github.com/BiggerPockets/.github/blob/main/.github/w...

Still a bit nicer to just do these yourself rather than reusing someone else’s project.

New comment by breckenedge in "GLM 5.2 and the coming AI margin collapse"

breckenedge — Tue, 07 Jul 2026 12:19:51 +0000

Like a junior engineer, I find the models to be too ambitious and unable to steer themselves at a high level yet. What I’ve done to address this is prompting the model to break down its plans into more atomic steps. For whatever reason, they’re still lazy at planning.

New comment by breckenedge in "Solid and Clean Code never felt solid or clean to me"

breckenedge — Wed, 01 Jul 2026 17:11:38 +0000

Programming is human. Obviously there will be cultures (and cults) that spring up and die down all the time. I probably pissed off a few colleagues over the years by rejecting their arguments because they were “appeals to authority” that I did not recognize as authorities in the particular problems we were solving at the time. Hate cargo cult programming, but admit I fell into that trap often enough in my early years. Gotta start somewhere.

New comment by breckenedge in "Oracle shed about 20k roles globally in the last year"

breckenedge — Tue, 23 Jun 2026 12:43:48 +0000

Oracle overcommitted on behalf of OpenAI, taking on debt to meet their obligations. Not that healthy companies are not also doing ridiculous layoffs, but in this case, Oracle does have to do some drastic things to get out of this tailspin.

New comment by breckenedge in "I built a small road chaos game in the browser"

breckenedge — Mon, 22 Jun 2026 19:46:44 +0000

Fyi the homepage is too small for my mobile browser (chrome, iPhone 15 pro) and appears to not support scrolling

New comment by breckenedge in "The software industry: annealing, but wrong"

breckenedge — Thu, 18 Jun 2026 23:28:25 +0000

It’s amazing how often I’ve discussed this from the perspective of “binary search”: you gotta make big jumps before you do narrow jumps.

Same for being stuck in local maxima: getting out of that requires big changes, not small-step optimizations.