Hacker News: pietz

New comment by pietz in "Claude Fable 5"

pietz — Tue, 09 Jun 2026 17:13:38 +0000

> On June 23, we’ll remove Fable 5 from those plans. Using it after that will require usage credits.

We've entered the phase where only companies will be able to afford state-of-the-art models.

New comment by pietz in "Claude Opus 4.8"

pietz — Thu, 28 May 2026 17:55:53 +0000

1. Benchmarks saturate 2. They select the most impressive improvments

New comment by pietz in "From Supabase to Clerk to Better Auth"

pietz — Wed, 06 May 2026 19:59:25 +0000

This comment is more ridiculous than ever in 2026.

New comment by pietz in "GPT-5.5"

pietz — Thu, 23 Apr 2026 18:38:58 +0000

OpenAI has been very generous with limit resets. Please don't turn this into a weird expectation to happen whenever something unrelated happens. It would piss me off if I were in their place and I really don't want them to stop.

New comment by pietz in "30 Days Running ChatGPT Plus, Claude Pro, and Google AI Pro in Parallel"

pietz — Thu, 23 Apr 2026 16:18:43 +0000

> Claude Opus 4.7 ($20 Pro tier) is the new coding king.

That's ridiculous. If you use Opus 4.7 for coding on the $20 tier, you'll hit the session limit within 20 minutes.

New comment by pietz in "Cal.com is going closed source"

pietz — Wed, 15 Apr 2026 16:00:28 +0000

This conclusion makes more sense to me, but maybe I'm too naive.

The media momentum of this threat really came with Mythos, which was like 2 or 3 weeks ago? That seems like a fairly short time to pivot your core principles like that. It sounds to me like they wanted to do this for other business related reasons, but now found an excuse they can sell to the public.

(I might be very wrong here)

New comment by pietz in "Trivy under attack again: Widespread GitHub Actions tag compromise secrets"

pietz — Tue, 24 Mar 2026 00:51:00 +0000

So by wanting to improve the security of my application, I ended up lowering the security of my application? Nice.

New comment by pietz in "Nano Banana 2: Google's latest AI image generation model"

pietz — Thu, 26 Feb 2026 16:25:06 +0000

I'm officially done with the Nano Banana name. It was fun, but can we go back just calling it Gemini Image?

New comment by pietz in "Voxtral Transcribe 2"

pietz — Wed, 04 Feb 2026 16:47:16 +0000

Do we know if this is better than Nvidia Parakeet V3? That has been my go-to model locally and it's hard to imagine there's something even better.

New comment by pietz in "Claude Code is suddenly everywhere inside Microsoft"

pietz — Mon, 02 Feb 2026 23:58:05 +0000

Why not just use it in the terminal? That's literally what it was built for.

New comment by pietz in "AGENTS.md outperforms skills in our agent evals"

pietz — Thu, 29 Jan 2026 21:39:48 +0000

Isn't it obvious that an agent will do better if he internalizes the knowledge on something instead of having the option to request it?

Skills are new. Models haven't been trained on them yet. Give it 2 months.

New comment by pietz in "Consent-O-Matic"

pietz — Sun, 18 Jan 2026 10:31:36 +0000

This idea/execution isn't new right? Can someone explain what makes this different/better? Is this the ublock Origin of cookie banner hiders?

New comment by pietz in "Anthropic blocks third-party use of Claude Code subscriptions"

pietz — Fri, 09 Jan 2026 18:11:50 +0000

Honest question: Why would I use Claude with OpenCode if I have a Claude Max subscription? Why not Claude Code?

New comment by pietz in "LMArena is a cancer on AI"

pietz — Thu, 08 Jan 2026 08:01:33 +0000

Uhm, yes that's why you rely on LMArena (core) results only to judge the answering style and structure. I thought this was common knowledge.

New comment by pietz in "Show HN: OfferGridAI – side-by-side comparison of real estate offers from PDFs"

pietz — Fri, 02 Jan 2026 15:20:35 +0000

2006: "This meeting could have been an e-mail"

2026: "This app could have been a prompt"

New comment by pietz in "We removed 80% of our agent's tools"

pietz — Wed, 24 Dec 2025 00:05:17 +0000

Hold up, so d0 is just Claude with access to the terminal?

Sounds like they just discovered that they don't have a product.

New comment by pietz in "Codex is a Slytherin, Claude is a Hufflepuff"

pietz — Tue, 23 Dec 2025 23:59:32 +0000

Weirdly, I find a higher signal to noise in this analogy than looking at benchmarks these days.

If you let your inner fanboy rest for a moment you realize Gemini 3, Claude Opus 4.5, and GPT 5.2 are all amazing. If two of them disappeared tomorrow, my AI assisted productiveness wouldn't change.

The 3% difference on benchmark X doesn't mean anything anymore. It's probably more helpful to compare them on character traits instead of numbers.

My one word to describe Claude would be "pleasant". It's just so nice to communicate with. GPT/Codex would be the "thorough". It finds and thinks of stuff the others don't. For Gemini 3, the jury is still out. It might be the smart kid on the block that's still a bit rough around the edges, but given that it's a preview things might change soon.

New comment by pietz in "Show HN: RenderCV – Open-source CV/resume generator, YAML to PDF"

pietz — Sun, 21 Dec 2025 18:24:45 +0000

I hear you. This boils town to personal opinion. I would have preferred to use an existing standard than introducing yet another one. The custom sections aren't something I've ever seen or needed anyway.

New comment by pietz in "Show HN: RenderCV – Open-source CV/resume generator, YAML to PDF"

pietz — Sun, 21 Dec 2025 16:16:26 +0000

A bit of a missed opportunity not to use the JSON Resume schema for this.

https://jsonresume.org/schema

New comment by pietz in "GPT-5.2-Codex"

pietz — Fri, 19 Dec 2025 11:14:23 +0000

That's a fair point and yet I deeply believe Codex is better here. After finishing a big task, I used two fresh instances of Claude and Codex to review it. Codex finds more issues in ~9 out of 10 cases.

While I prefer the way Claude speaks and writes code, there is no doubt that whatever Codex does is more thorough.