Hacker News: stephantul

New comment by stephantul in "Prioritize mental health, and why communication is so important"

stephantul — Wed, 15 Jul 2026 13:50:37 +0000

As mentioned by a sibling comment: this is an insensitive take.

It takes a lot of courage to write down one’s struggles for all the world to see. Your analysis denies the OP their self-reflection, and instead reduces it to a thing you happened to find in your own life.

New comment by stephantul in "Show HN: Only 1 of 4,356 reachable MCP servers is ready for the 2026-07-28 spec"

stephantul — Sun, 12 Jul 2026 15:59:36 +0000

I am interested in why you chose to do this, and publish it with the headline you used. Was it to learn something? Or to get publicity for another project?

Tbh, this sounds like fear mongering to me. Of course the statement “99.9% of servers are not compliant” sounds impressive, but then it turns spec hasn’t even been released yet.

Also some general feedback: the whole thing looks generated, as does the comment I am replying to.

New comment by stephantul in "Why we're moving off Cloudflare Durable Objects"

stephantul — Thu, 09 Jul 2026 17:24:29 +0000

Why do all this work and then let an ai write the blog post.

New comment by stephantul in "Klara and the Sun Essay Contest – $1k Prize – AI Use Allowed"

stephantul — Thu, 02 Jul 2026 19:49:44 +0000

Ok, thanks!

New comment by stephantul in "Klara and the Sun Essay Contest – $1k Prize – AI Use Allowed"

stephantul — Thu, 02 Jul 2026 19:23:17 +0000

It’s personal ad, basically. The author is trying to get a job as an evaluator somewhere and is hoping that putting 1000$ on the line will get them enough publicity to land them an interview/get a job somewhere.

New comment by stephantul in "Klara and the Sun Essay Contest – $1k Prize – AI Use Allowed"

stephantul — Thu, 02 Jul 2026 19:07:17 +0000

Is it even legal to publish excerpts of books like this? Or does this fall under some kind of exemption/fair use clause?

New comment by stephantul in "OpenRA"

stephantul — Sat, 27 Jun 2026 14:34:35 +0000

Thanks for introducing me to the article! I’ve experienced this myself but didn’t know it had a name.

New comment by stephantul in "Good results fine tuning a local LLM like Qwen 3:0.6B to categorize questions"

stephantul — Mon, 22 Jun 2026 08:33:42 +0000

A non-autoregressive transformer trained with a classification objective.

New comment by stephantul in "Developers don't understand CORS (2019)"

stephantul — Sun, 21 Jun 2026 06:23:30 +0000

The second part of this comment is not what I expected. I also don’t think it is true. I got bit by a CORS error at work recently that passed by Claude, copilot, and another senior engineer.

New comment by stephantul in "The Token Compression Illusion: Why I'm Skeptical of RTK"

stephantul — Fri, 19 Jun 2026 04:34:48 +0000

We’ve been on the receiving end of this complaint with Semble. I think it is a valid complaint, but constructing a benchmark for this kind of thing is just very difficult and expensive because of the (harness) x (model) x (mcp/cli) combination.

With traditional ml/tooling, not showing benchmarks was usually a red flag. But for llm tooling, I’m not so sure.

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

stephantul — Wed, 17 Jun 2026 12:32:11 +0000

Ha thanks, it was pink a while ago

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

stephantul — Wed, 17 Jun 2026 11:48:36 +0000

Extreme programming in a nutshell. I like doing this to features: build it, then take it down and rebuild but better.

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

stephantul — Wed, 17 Jun 2026 11:38:26 +0000

Puppy slush automatically pushed through vents into your codebase

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

stephantul — Wed, 17 Jun 2026 09:31:36 +0000

Thanks! This is very similar indeed. Related: I see a lot of “drive-by” PRs by agents, who obviously have no intent of ever maintaining the code they wrote.

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

stephantul — Wed, 17 Jun 2026 09:29:43 +0000

I’m not sure I share your view of PRs. I still see submitting PRs as something that puts pressure on maintainers. Even incorrect PRs take time to verify and review.

I also don’t see how this differs between the “gap” and the “fence” part of the metaphor. Whether someone submits a rewrite/removal (fence) or a new feature (gap) for PR review, it’s still going to cost me attention.

From Chesterton's fence to Chesterton's gap

stephantul — Wed, 17 Jun 2026 06:50:47 +0000

Article URL: https://stephantul.github.io/blog/unfence/

Comments URL: https://news.ycombinator.com/item?id=48566727

Points: 86

# Comments: 56

New comment by stephantul in "Are insecure code completions in PyCharm a vulnerability?"

stephantul — Thu, 11 Jun 2026 05:38:33 +0000

It’s an interesting question: I’d say this is more of a vulnerability creator than the actual vulnerability.

Similar to how using very difficult technologies makes you more likely to create code with vulnerabilities: the technologies are not the vulnerability, but it’s easier to cause them.

New comment by stephantul in "Is Grep All You Need? How Agent Harnesses Reshape Agentic Search"

stephantul — Tue, 09 Jun 2026 17:26:10 +0000

This paper oversells on the title. Like, what is chronos, which embedding model was used, which reranker, how was the reranking done, why is chronos much better than claude code

New comment by stephantul in "Cloudflare Turnstile requiring fingerprintable WebGL"

stephantul — Sun, 31 May 2026 17:03:12 +0000

Sure, the whole premise is exactly that proof of work reduces the value of scraping, while having negligible impact on users. If the data is so valuable that bot operators are willing to pay 10s of cpu, then other measures are necessary.

Nevertheless even for these high value cases, you can still argue that it disincentivizes the business model, it becomes less efficient.

New comment by stephantul in "Cloudflare Turnstile requiring fingerprintable WebGL"

stephantul — Sun, 31 May 2026 15:46:48 +0000

Because it destroys the economics of scraping. It’s too expensive with proof of work, or at least not as economically viable