Hacker News: nfw2

New comment by nfw2 in "Scientists Figured Out How Eels Reproduce (2022)"

nfw2 — Sun, 05 Apr 2026 22:14:33 +0000

I think it's reasonable to knock on someone for concluding a wildly incorrect theory (eg generating out of mud) even when lacking evidence pointing to the correct answer. Aristotle did this a lot. The correct position in these scenarios is one of uncertainty.

New comment by nfw2 in "How many products does Microsoft have named 'Copilot'?"

nfw2 — Sun, 05 Apr 2026 01:14:41 +0000

Is there a copilot for Microsoft flight simulator though?

New comment by nfw2 in "Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw"

nfw2 — Sat, 04 Apr 2026 20:22:35 +0000

Sure but if the mechanism that bans openclaw also bans me, I still get banned

New comment by nfw2 in "Delve removed from Y Combinator"

nfw2 — Sat, 04 Apr 2026 04:54:44 +0000

It's not just about delve. It's about yc's model. YC encourages YC companies to trust other YC companies even though they are early.

If you can't trust your batch mates for something as crucial as compliance, the model doesn't work.

New comment by nfw2 in "Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw"

nfw2 — Sat, 04 Apr 2026 01:22:33 +0000

I don't understand exactly what is being banned. I have a vibe coded context manager + chat thread UI that I use to manage multiple claude code cli sessions simultaneous. Is this allowed? If not how would this get identified vs other cli usage? How is this different than openclaw?

New comment by nfw2 in "Every layer of review makes you 10x slower"

nfw2 — Tue, 17 Mar 2026 19:34:40 +0000

what do you mean exactly? you are asking random people to share their company's code with you?

New comment by nfw2 in "Every layer of review makes you 10x slower"

nfw2 — Tue, 17 Mar 2026 08:52:51 +0000

from article:

1. Whoa, I produced this prototype so fast! I have super powers!

2. This prototype is getting buggy. I’ll tell the AI to fix the bugs.

3. Hmm, every change now causes as many new bugs as it fixes.

4. Aha! But if I have an AI agent also review the code, it can find its own bugs!

5. Wait, why am I personally passing data back and forth between agents

6. I need an agent framework

7. I can have my agent write an agent framework!

8. Return to step 1

the author seems to imply this is recursive when it isn't. when you have an effective agent framework you can ship more high quality code quickly.

New comment by nfw2 in "A sane but bull case on Clawdbot / OpenClaw"

nfw2 — Thu, 05 Feb 2026 19:00:53 +0000

> Dear Brandon.

not a sentence

> King regards.

not a sentence

> I'll admit to the pedantry but

missing comma between independent clauses

New comment by nfw2 in "Bitcoin tumbles below $70k, wiping out gains since Trump 2024 win"

nfw2 — Thu, 05 Feb 2026 18:59:25 +0000

It's a reference to the Bill O'Reilly line about tides

New comment by nfw2 in "A sane but bull case on Clawdbot / OpenClaw"

nfw2 — Thu, 05 Feb 2026 01:59:47 +0000

don't be pedantic about grammar and then get your own grammar wrong

New comment by nfw2 in "A sane but bull case on Clawdbot / OpenClaw"

nfw2 — Thu, 05 Feb 2026 01:58:04 +0000

It is combination of:

- Cron-style heartbeat manager

- Easy customization with markdown only

- Good out-of-box memory management that just works

- Good set of tools out-of-box that just work

Like Jack Dorsey said about project success, limit number of details and make those details perfect

New comment by nfw2 in "A sane but bull case on Clawdbot / OpenClaw"

nfw2 — Thu, 05 Feb 2026 01:46:16 +0000

On the other hand, other humans may have intrinsic interests outside of your control that may lead them to harm you despite the mechanisms you mentioned, whereas bots by default don't have such motives.

New comment by nfw2 in "Study: Minimal evidence links social media, gaming to teen mental health issues"

nfw2 — Mon, 19 Jan 2026 22:43:50 +0000

It's sort of funny that the headline right underneath this one on hn right now is about social media research having ties to industry

New comment by nfw2 in "Predicting OpenAI's ad strategy"

nfw2 — Sun, 18 Jan 2026 21:34:00 +0000

So another platform disrupting the duopoly would be good, no?

New comment by nfw2 in "Predicting OpenAI's ad strategy"

nfw2 — Sun, 18 Jan 2026 16:08:52 +0000

In order to sell anything, people need to know about it. Google and Meta provide a way to make this possible. If they didn't exist, you wouldn't somehow have a more affordable way to get people to know about your product. However frustrating the current situation is, it is still more accessible than needing access to the airwaves or print media to try to sell anything new.

New comment by nfw2 in "I hate GitHub Actions with passion"

nfw2 — Wed, 14 Jan 2026 21:26:32 +0000

I am surprised that these sort of declarative specs are so popular in certain domains. Essentially you always seem to be putting settings into the ether and hoping they interact with each other in the way you expect.

I prefer an api with documented contracts between its abstractions

New comment by nfw2 in "AI coding assistants are getting worse?"

nfw2 — Fri, 09 Jan 2026 07:08:27 +0000

People who think syntax highlighting is useful are a cargo cult?

New comment by nfw2 in "AI coding assistants are getting worse?"

nfw2 — Fri, 09 Jan 2026 07:07:24 +0000

That's the whole point. The sky is blue is trivially observable. Any claim that someone has disproven something that is trivially observable should be met with skepticism.

If you have something that needs to be done, and an agent goes and does the whole thing for you without mistakes, it is trivially observable that that is useful. That is the definition of usefulness.

New comment by nfw2 in "AI coding assistants are getting worse?"

nfw2 — Fri, 09 Jan 2026 06:54:33 +0000

This is what you claimed the bar was "it just should be higher than 'I feel like'"

Now you are moving it because your statement is provably false.

Your criticism of it is based on vibes. What specifically is wrong with the methodologies?

One of them broke randomly developers into two groups, one with access to ai and one without, timed them to complete the same task, and compared the results. That seems fine? Any measurement of performance in a lab environment comes with caveats, but since real world accounts you dismiss as vibes, that seems like the best you can do.

New comment by nfw2 in "AI coding assistants are getting worse?"

nfw2 — Fri, 09 Jan 2026 06:45:43 +0000

Ironically the start of this thread was bemoaning the use of anecdotal evidence