Hacker News: deanalyzer

New comment by deanalyzer in "Towards a harness that can do anything"

deanalyzer — Thu, 16 Jul 2026 03:14:12 +0000

Exactly right. There are many different domains that AI can be helpful in, and I am frustrated by how it's used to process information in a lossy manner.

New comment by deanalyzer in "Ask HN: What Are You Working On? (July 2026)"

deanalyzer — Mon, 13 Jul 2026 03:14:59 +0000

Yes, and what's scary is that I can easily imagine HR departments loving these tools and using them at scale.

New comment by deanalyzer in "Ask HN: What Are You Working On? (July 2026)"

deanalyzer — Mon, 13 Jul 2026 03:11:59 +0000

this looks incredibly useful! I've also run into similar problems with code review and been building similar tooling with the same idea (reconstructing the changes into entities, and finding focal/important changes), but haven't gone as far as this.

New comment by deanalyzer in "The Trouble with Effortless Code"

deanalyzer — Mon, 13 Jul 2026 00:15:38 +0000

This is nicely put.

One possible implication is that this calls for a new wave of developer tools designed to introduce friction between human cognition and code. This would be a very different philosophy from that of developer tools in the past.

New comment by deanalyzer in "Optimization Solver as a Service"

deanalyzer — Sun, 12 Jul 2026 05:57:35 +0000

This could be interesting, but it badly needs systematic benchmarking results. It is not difficult to get Claude Code or Codex to install and run a solver locally, so the tool’s current value proposition is fairly muddled.

If there were evidence that it offered better performance, I might consider running larger workloads on it.

New comment by deanalyzer in "We made Grok 4.5, GPT-5.5, and Claude build the same apps"

deanalyzer — Thu, 09 Jul 2026 06:08:05 +0000

Yes, I wonder how the verdicts would hold under a blinded test. This analysis read like the authors going out of their way to be supportive of Grok.

New comment by deanalyzer in "An interactive explorer for Benford's Law across real datasets"

deanalyzer — Wed, 08 Jul 2026 04:07:06 +0000

I learned about Benford's law over a decade ago, and I always found it beautiful and elegant. But surely, fraudsters have become more sophisticated by now. I wonder if you asked an AI to commit fraud, if it would be clever enough to avoid such mistakes.