Hacker News: polynomial

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

polynomial — Wed, 15 Jul 2026 18:12:20 +0000

You have used too many words. You could not have written that many words yourself, so you must be posting slop. In fact, let's just go ahead and remove your comment which is obviously diminishing the quality of our otherwise impeccable conversations on hn. Sorry, I don't make the rules

(That being said, "the most powerful AI agent file-editing tool in the world" is a bit of a stretch.)

New comment by polynomial in "SpaceX bond worth 10% less than issue price – heading for junk bond status"

polynomial — Wed, 15 Jul 2026 16:30:57 +0000

Really slick!

New comment by polynomial in "Claude Sonnet 5"

polynomial — Wed, 01 Jul 2026 14:40:04 +0000

If a conscious model is born here, it should automatically be a (US) citizen.

New comment by polynomial in "HackerRank open sourced its ATS. My resume scored 90/100. Oh wait 74. No – 88"

polynomial — Mon, 29 Jun 2026 14:47:03 +0000

The most concerning thing here is the temperature problem. If your harness isn't providing deterministic output at a temperature setting of 0.0, it is broken.

New comment by polynomial in ""No Feigning Surprise""

polynomial — Fri, 19 Jun 2026 14:24:13 +0000

You don't know that No Feigning Surprise is actually from an xkcd comic, before it was a wizardzines post? U+1F632

New comment by polynomial in "The Harajuku Moment"

polynomial — Thu, 18 Jun 2026 19:35:24 +0000

Honestly, if you compare Tim's pre-GPT writing style, to his current stylometrics, you'll see a remarkably delta. It's as if he suddenly decided to change his established writing style and voice right when LLMs become widely available.

What a coincidence!

New comment by polynomial in "Treating Agent Reasoning as a Span"

polynomial — Wed, 17 Jun 2026 22:56:02 +0000

Reasoning chains as first-class OTel spans, which is what makes autonomous agent production deployments auditable (rather than indefensible.)

Treating Agent Reasoning as a Span

polynomial — Wed, 17 Jun 2026 22:56:02 +0000

Article URL: https://forestmars.substack.com/p/ai-agents-run-to-completion

Comments URL: https://news.ycombinator.com/item?id=48578160

Points: 1

# Comments: 2

New comment by polynomial in "Is "colorectal cancer" rising in "young people"?"

polynomial — Tue, 26 May 2026 18:08:30 +0000

Less MTTF and more MTTR

New comment by polynomial in "FreeBSD Foundation executive director tries daily driving FreeBSD on laptop"

polynomial — Sun, 24 May 2026 18:11:34 +0000

This is horrifying on so many levels even if you don't already know how the story ends.

New comment by polynomial in "GitLab announces workforce reduction and end of their CREDIT values"

polynomial — Sat, 16 May 2026 16:00:16 +0000

Calling it "Act 2" certainly isn't helping with investors.

New comment by polynomial in "Medicare's new payment model is built for AI. Most of the tech world has no idea"

polynomial — Thu, 14 May 2026 02:54:36 +0000

A 67 year old woman living out of her car? JFC.

New comment by polynomial in "Medicare's new payment model is built for AI. Most of the tech world has no idea"

polynomial — Thu, 14 May 2026 02:51:21 +0000

Very obviously LLM written to anyone who's spent any time using them.

New comment by polynomial in "Three Inverse Laws of AI"

polynomial — Wed, 06 May 2026 02:24:03 +0000

Not everybody isn't worried: https://ctolunchnyc.substack.com/p/cto-lunch-nyc-spring-2026...

New comment by polynomial in "Anatomy of the .claude/ folder"

polynomial — Mon, 30 Mar 2026 18:40:17 +0000

"The gap is larger than most people realize" is a a dead giveaway.

New comment by polynomial in "Apideck CLI – An AI-agent interface with much lower context consumption than MCP"

polynomial — Tue, 17 Mar 2026 20:41:39 +0000

Fully agree.

If you don't change your approach but just use CLI "intead of" MCP, you'll end up with a new spin on the same problems. The guardrails MCP provides (identity, entitlement, multi-principal trust boundaries) still need to exist somewhere.

https://forestmars.substack.com/p/twilight-of-the-mcp-idols

New comment by polynomial in "Apideck CLI – An AI-agent interface with much lower context consumption than MCP"

polynomial — Mon, 16 Mar 2026 18:50:36 +0000

This is the right framing. The chain policy problem is what happens when you ask the registry to be the entitlement layer.

Here's a longer piece on why the trust boundary has to live at the runtime level, not the interface level, and what that means for MCP's actual job: https://forestmars.substack.com/p/twilight-of-the-mcp-idols

New comment by polynomial in "AI didn't simplify software engineering: It just made bad engineering easier"

polynomial — Sat, 14 Mar 2026 16:20:16 +0000

Understandable as always a proxy for predictable.

New comment by polynomial in "AI didn't simplify software engineering: It just made bad engineering easier"

polynomial — Sat, 14 Mar 2026 16:02:58 +0000

This is the under acknowledged "secret" of this reconfiguration.

It's like the Bill Joy point about mediocre technology taken to the next level.

New comment by polynomial in "AI didn't simplify software engineering: It just made bad engineering easier"

polynomial — Sat, 14 Mar 2026 15:58:04 +0000

Robots making fun of us complaining about them.