Hacker News: jmcqk6

New comment by jmcqk6 in "If AI Writes All the Code, What Do the Programmers Do?"

jmcqk6 — Tue, 28 Jul 2026 16:47:08 +0000

There are three things programmers bring:

Salience - Agents only know what we bring to their attention

Judgment - Agents cannot make decisions in the larger business context

Responsibility - Agents do not care if they crash the system

New comment by jmcqk6 in "How we measured AI writing across arXiv, and where the measurement breaks"

jmcqk6 — Mon, 20 Jul 2026 18:48:05 +0000

Extend it to scan papers from pre-2020. That should give you a better baseline accuracy for your detection system.

New comment by jmcqk6 in "Linux 0.11 rewritten in idiomatic Rust, boots in QEMU"

jmcqk6 — Tue, 14 Jul 2026 16:43:07 +0000

How did it kill the product? It's still cranking along pretty good.

New comment by jmcqk6 in "Don't you mean extinct?"

jmcqk6 — Mon, 13 Jul 2026 15:37:42 +0000

I've been thinking of it as a "conservation of cognition". there is some fundamental about of cognition that needs to be spent in order to keep things moving. LLMs do not reduce that, they only change it.

New comment by jmcqk6 in "Rewriting Bun in Rust"

jmcqk6 — Thu, 09 Jul 2026 17:08:43 +0000

ghostty is a zig project too!

New comment by jmcqk6 in "Collapse of Atlantic Currents May Already Be 'Locked In'"

jmcqk6 — Wed, 08 Jul 2026 16:13:53 +0000

You can't keep people from being stupid via the language you use. People who have the reaction you describe would not magically "get it" if different language is used.

New comment by jmcqk6 in "Zuckerberg says AI agent development going slower than expected"

jmcqk6 — Mon, 06 Jul 2026 16:52:37 +0000

> Absolutely true, however my experience says that the correlation between "good software engineering practices" and "positive business outcomes" is, at best, small.

One of the most uncomfortable truths about our profession is that there is no floor to how bad software can be while still making people billions of dollars.

New comment by jmcqk6 in "CursorBench 3.1"

jmcqk6 — Thu, 02 Jul 2026 19:12:52 +0000

I can't speak to benchmarks, but I have used Composer 2.5 extensively and it's performed quite well in my real world tasks.

New comment by jmcqk6 in "From Chesterton's fence to Chesterton's gap"

jmcqk6 — Mon, 22 Jun 2026 17:19:27 +0000

Why does it need to provide guidance about that? It's one step along the way of cultivating wisdom, not the destination.

New comment by jmcqk6 in "From Chesterton's fence to Chesterton's gap"

jmcqk6 — Wed, 17 Jun 2026 15:44:38 +0000

I don't think you've understood the lesson here. Chesterton's fence is not about keeping systems in place. It is about how you approach changing the system.

New comment by jmcqk6 in "Wolfram Language and Mathematica version 15"

jmcqk6 — Wed, 17 Jun 2026 15:41:07 +0000

yeah he's not a crank, just an asshole. Taking credit for work did by his employees, to the point of suing them. The only significant discovery to come out of his CA work was completed by an employee, who wolfram sued when he published a paper and gave a talk on it.

New comment by jmcqk6 in "Kimi K2.7-Code: open-source coding model with better token efficiency"

jmcqk6 — Fri, 12 Jun 2026 15:35:51 +0000

I'm using Composer extensively, and it works great for me. Your experiences are not universal.

New comment by jmcqk6 in "German ruling declares Google liable for false answers in AI Overviews"

jmcqk6 — Wed, 10 Jun 2026 15:29:19 +0000

Lots of people in the US getting left behind too.

New comment by jmcqk6 in "Cursor Introduces Composer 2.5"

jmcqk6 — Tue, 19 May 2026 17:53:44 +0000

That does not match my experience. Composer 2 was fantastic for my uses, and I hit Composer 2.5 with some very difficult things last night, which it handled fast and effectively. I don't really care about benchmarks. I care about practice, and in practice, it's been very very good for me.

New comment by jmcqk6 in "Cursor Introduces Composer 2.5"

jmcqk6 — Tue, 19 May 2026 17:51:31 +0000

I've been using cursor for over a year for my personal projects. At work, I use Claude Code, and so I've been wondering if I'm missing something in the other agents.

Over the last week, I tried out two other agents on my personal projects: dirac and forgecode, after seeing impressive results from both of them on terminal bench.

After a good amount of testing, and over $100 in open router spend, I'm back to cursor.

I really liked forgecode the best, and it feels better than claude code, but cursor definitely feels best to me. Composer 2.5 is fast and effective, and it makes a huge difference. I was running `forge` with Opus, and it was taking dozens of minutes to do things, and the feedback loop was so slow.

The previous version of composer was also much faster, and it makes a difference. Maybe people like context switching, but I prefer to stay focussed on the task in front of me, and I'm reviewing the code carefully.

I think that's a pretty good moat. I was ready to end my subscription a week ago, and now I'm back after learning the grass is not necessarily greener on the other side of the fence.

New comment by jmcqk6 in "The AI Backlash Could Get Ugly"

jmcqk6 — Wed, 13 May 2026 23:13:03 +0000

I didn't imply anything. I just called out the emotional reality. There are a lot of externalized pain in the world today, and little recourse to addressing it. You can try telling people that they are naive and need to look at the big picture, but you might not see much success at getting your point across.

New comment by jmcqk6 in "The AI Backlash Could Get Ugly"

jmcqk6 — Wed, 13 May 2026 15:37:39 +0000

> There will be suffering during transition and there will be many that don’t fare well

Yeah, and the people suffering are not going to like that. If people are afraid of being in that group, then they will not be very happy about it.

If you put yourself in the shoes of someone suffering from AI, how comforting do you think your observations here are?

New comment by jmcqk6 in "Uber torches 2026 AI budget on Claude Code in four months"

jmcqk6 — Fri, 01 May 2026 18:47:01 +0000

It sounds like this has a pretty falsifiable claim here - is the revenue attributed to a tax thing? Then it's clearly not attributable to code.

I agree that the macro picture would speak for itself. Can you point to any macro level detail that is indeed cleanly showing benefits from increased productivity from LLMs?

New comment by jmcqk6 in "The Zig project's rationale for their anti-AI contribution policy"

jmcqk6 — Thu, 30 Apr 2026 18:00:08 +0000

You're still talking about compute resources that need to be paid for and maintained for that. Spamming AI PR's is going to cost a lot of money.

New comment by jmcqk6 in "The Zig project's rationale for their anti-AI contribution policy"

jmcqk6 — Thu, 30 Apr 2026 16:23:30 +0000

Those things cost resources, and now you're introducing a new attack vector: open up a bunch of shit PRs, burn a lot of cash for the target organization.