Hacker News: ayhanfuat

New comment by ayhanfuat in "I'm Done with Mullvad"

ayhanfuat — Mon, 20 Jul 2026 08:09:55 +0000

Previous discussion: The CEO of Mullvad is the main financer of the Swedish Örebro party 695 points | 1784 comments (https://news.ycombinator.com/item?id=48717469)

It also has a comment from the other founder: https://news.ycombinator.com/item?id=48696800

New comment by ayhanfuat in "Claude Code: Anatomy of a Misfeature"

ayhanfuat — Fri, 17 Jul 2026 15:20:31 +0000

I really hate this direction both Anthropic and Open AI are following. They are in this silly competition whose model/harness can go unattended the longest, no matter what. And it is never explicit, you learn about it after you get bitten by it. Claude Code has auto mode which is supposed to take over permission prompts but no, they had to couple that with “I will assume this is what the user wants” and made it unusable.

New comment by ayhanfuat in "30papers.com – Ilya's 30 essential ML papers, in a beginner friendly format"

ayhanfuat — Tue, 07 Jul 2026 17:58:51 +0000

I think someone on Twitter made it up. It was also 40 papers, not 30. https://dallasinnovates.com/exclusive-qa-john-carmacks-diffe...

New comment by ayhanfuat in "What Emily Bender meant by "stochastic parrots""

ayhanfuat — Mon, 06 Jul 2026 15:38:30 +0000

Here is what Jeff Dean said about the firing at the time: https://docs.google.com/document/d/1f2kYWDXwhzYnq8ebVtuk9CqQ...

New comment by ayhanfuat in "The deadly rise of giant trucks and SUVs"

ayhanfuat — Tue, 23 Jun 2026 17:59:12 +0000

It is worth reading the interactive Times article. Amazing piece of work https://www.nytimes.com/interactive/2026/06/21/us/trucks-suv...

Being oncall taught me everything

ayhanfuat — Sat, 23 May 2026 17:50:10 +0000

Article URL: https://yaoyue.org/blog/2026-oncall/

Comments URL: https://news.ycombinator.com/item?id=48249619

Points: 2

# Comments: 0

New comment by ayhanfuat in "An update on recent Claude Code quality reports"

ayhanfuat — Thu, 23 Apr 2026 18:24:38 +0000

They feel they're in a position to make important trade-off decisions on behalf of the user. "It's just slightly worse, I'll sneak this change in" is not something to be tolerated, whether it actually turns out to be much worse or not. Their adaptive thinking mess has caused a ton of work for me. I know a lot of people are saying Codex is actually better now. I don't agree but I'm switching to it because it's much more reliable.

New comment by ayhanfuat in "An update on recent Claude Code quality reports"

ayhanfuat — Thu, 23 Apr 2026 18:07:08 +0000

Reading the "Going forward" section I see that they have zero understanding of the main complaints.

New comment by ayhanfuat in "Claude Design"

ayhanfuat — Fri, 17 Apr 2026 21:24:11 +0000

Same for me. It jumped to 11% on the first prompt and now increasing steadily. I think I will hit the limits without seeing a hi-fi version.

New comment by ayhanfuat in "Pro Max 5x Quota Exhausted in 1.5 Hours Despite Moderate Usage"

ayhanfuat — Sun, 12 Apr 2026 14:55:08 +0000

> * Turn on max thinking on every session. It save tokens overall because I’m not correcting it of having it waste energy on dead paths.

This is definitely true. Ever since I realized there is an /effort max option I am no longer fighting it that much and wasting hours.

Agentsview: A local-first desktop and web app for browsing AI agent sessions

ayhanfuat — Sun, 12 Apr 2026 12:43:28 +0000

Article URL: https://github.com/wesm/agentsview

Comments URL: https://news.ycombinator.com/item?id=47738991

Points: 1

# Comments: 0

Pausing new GitHub Copilot Pro trials

ayhanfuat — Fri, 10 Apr 2026 21:27:49 +0000

Article URL: https://github.blog/changelog/2026-04-10-pausing-new-github-copilot-pro-trials/

Comments URL: https://news.ycombinator.com/item?id=47723872

Points: 4

# Comments: 1

New comment by ayhanfuat in "Scientists invented a fake disease. AI told people it was real"

ayhanfuat — Fri, 10 Apr 2026 10:48:12 +0000

> Even if readers didn’t make it all the way to the ends of the papers, they would have encountered red flags early on, such as statements that “this entire paper is made up” and “Fifty made-up individuals aged between 20 and 50 years were recruited for the exposure group”.

> What is the recommendation here? Should the agent take everything published in a skeptical way?

Not everything. Maybe some things that are explicitly called made-up.

Nteract: Native Interactive Notebooks

ayhanfuat — Thu, 02 Apr 2026 00:49:44 +0000

Article URL: https://www.nteract.io/

Comments URL: https://news.ycombinator.com/item?id=47608665

Points: 3

# Comments: 0

New comment by ayhanfuat in "Copilot edited an ad into my PR"

ayhanfuat — Mon, 30 Mar 2026 13:13:14 +0000

I stand corrected. GitHub team confirmed it's their Copilot ad.

New comment by ayhanfuat in "Copilot edited an ad into my PR"

ayhanfuat — Mon, 30 Mar 2026 06:22:52 +0000

Yes. The same message in GitLab: https://gitlab.tudelft.nl/thomasvermeule/GeneralAviationAirc...

New comment by ayhanfuat in "Show HN: Relay – The open-source Claude Cowork for OpenClaw"

ayhanfuat — Thu, 26 Mar 2026 11:03:39 +0000

These seem misleading. Cowork's VM is not on Anthropic servers?

> Local file access >> Relay: Truly local >> Cowork: Sandboxed VM on Anthropic's servers

> The bottom line: Claude Cowork is excellent for personal productivity on Anthropic's cloud. Relay is for teams and companies that need data sovereignty, compliance-ready audit trails, and model freedom — all on their own infrastructure.

New comment by ayhanfuat in "Why I forked httpx"

ayhanfuat — Wed, 25 Mar 2026 08:49:44 +0000

More related drama: The Slow Collapse of MkDocs (https://fpgmaas.com/blog/collapse-of-mkdocs/)

New comment by ayhanfuat in "How I'm Productive with Claude Code"

ayhanfuat — Mon, 23 Mar 2026 21:54:39 +0000

I don't know if I am just in an unlucky A/B assignment or anything but I really don't understand people juggling multiple agent sessions. For me Opus 4.6 High performance went from unbelievable to mediocre. And this keeps happening making the whole agentic coding very unreliable and frustrating. I do use it but I have to babysit and I get overwhelmed even with a single session.

New comment by ayhanfuat in "Anthropic takes legal action against OpenCode"

ayhanfuat — Thu, 19 Mar 2026 20:31:47 +0000

It revolves around how Open AI has much better models and how Claude Code engineers are a bunch of kids (which is kind of ironic).