Hacker News: sauwan

New comment by sauwan in "Gemini 3.5 Flash"

sauwan — Tue, 19 May 2026 18:46:46 +0000

Yeah, bummer. I was very excited for this release, but this killed it.

New comment by sauwan in "GPT‑5.3‑Codex‑Spark"

sauwan — Thu, 12 Feb 2026 19:31:57 +0000

It's either more expensive or dumber.

New comment by sauwan in "Ask HN: Do you have any evidence that agentic coding works?"

sauwan — Tue, 20 Jan 2026 20:14:39 +0000

>My wife and I had a really complicated spreadsheet for tracking how much we owed our babysitter – it was just complex enough to not really fit into a spreadsheet easily. I vibecoded a command line tool that's made it a lot easier.

Ok, please help me understand. Or is this more of a nanny?

New comment by sauwan in "Openwork – MIT-Licensed Cowork Alternative Based on OpenCode and Dev-Browser"

sauwan — Wed, 14 Jan 2026 19:47:19 +0000

As a Linux and Windows user I'm feeling unseen.

New comment by sauwan in "Floss Before Brushing"

sauwan — Wed, 29 Oct 2025 17:42:35 +0000

Well, the benefit here is the application of fluoride, which isn't something most people are actively thinking about maximizing.

New comment by sauwan in "Gemini 3.0 spotted in the wild through A/B testing"

sauwan — Thu, 16 Oct 2025 18:58:34 +0000

For pure text responses, agree 100%. Gemini falls way short on tool/function calling, and it's not very token-efficient for those of us using the API. But if they can fix those two things or even just get them in the same ballpark like they did with flash and flash-lite, it would easily become my primary model.

New comment by sauwan in "I tracked Amazon's Prime Day prices. We've been played"

sauwan — Fri, 10 Oct 2025 13:43:33 +0000

Hah, I quit Prime and they just gave it back to me. No charge. I can't cancel it. I can't figure it out, but perhaps they realized that their margin on me before I canceled was well over the cost of Prime? I'm not sure, but I still only use it a fraction of what I used to...

New comment by sauwan in "Qwen3-Next"

sauwan — Fri, 12 Sep 2025 12:16:45 +0000

Long running agents?

New comment by sauwan in "Apple Watch Ultra 3"

sauwan — Tue, 09 Sep 2025 18:41:01 +0000

Yeah, Apple watches are a non-starter for me. Zero chance I'm charging my watch daily.

New comment by sauwan in "Show HN: VoiceGecko – System-wide voice-to-text that types anywhere"

sauwan — Wed, 03 Sep 2025 16:47:59 +0000

Does this use a local STT model, or is our data leaving our computer?

New comment by sauwan in "Volkswagen gates a new vehicle's full horsepower behind monthly subscription"

sauwan — Mon, 18 Aug 2025 20:49:23 +0000

So, if you don't subscribe, do they pay you to offset the worse gas mileage your car has to carry around but never have access to?

I'm not a lawyer, but is this not a class action suit waiting to happen?

New comment by sauwan in "I'm worried it might get bad"

sauwan — Wed, 13 Aug 2025 15:32:29 +0000

Presumably, AI has advanced in 10 years?

New comment by sauwan in "Show HN: AgentMail – Email infra for AI agents"

sauwan — Thu, 31 Jul 2025 21:18:48 +0000

This is perfect timing for me - was just thinking about how to do this. But pricing is a bit steep for a startup currently looking to prove the market. Would you consider a cheaper option (e.g. 1 free inbox, or maybe $20/mo for 5 agent inboxes and a more limited storage level)? I'm building something that I might consider this for, but I don't know how long my runway is before I get sustainable client revenue, so $100/month is a deep hole being burned in my personal pocket before I can prove my MVP out.

New comment by sauwan in "Claude Code weekly rate limits"

sauwan — Mon, 28 Jul 2025 20:56:00 +0000

Would be great to see how our previous months usage stacked up and when, if at all, we would have been rate limited.

I'd be pretty surprised if I were to get rate limited, but I do use it a fair amount and really have no feel for where I stand relative to other users. Am I in the top 5%? How should I know?

New comment by sauwan in "First American pope elected and will be known as Pope Leo XIV"

sauwan — Thu, 08 May 2025 18:16:28 +0000

I liked calling him the "Ope Pope"

New comment by sauwan in "Medium Is the New Large"

sauwan — Wed, 07 May 2025 20:12:30 +0000

It's not cheaper than Deepseek V3.1, though, and Deepseek outperforms on nearly everything. And only between 1- 3x the throughput based on the openrouter metrics (near equivalent throughput if you use an FP8 quant). Wish I could be a little more excited about this one.

New comment by sauwan in "Gemini 2.5 Pro Preview"

sauwan — Tue, 06 May 2025 16:51:22 +0000

I'd be surprised if this was a new base model. It sounds like they just did some post-training RL tuning to make this version specifically stronger for coding, at the expense of other priorities.

New comment by sauwan in "A senior Apple exec could be jailed in Epic case"

sauwan — Thu, 01 May 2025 17:37:46 +0000

I'd agree with you if that cut was 5, maybe 10%. I just don't understand how they can justify 30% outside of "you don't have any other choice".

New comment by sauwan in "Gemini 2.5"

sauwan — Tue, 25 Mar 2025 21:13:24 +0000

I'm assuming this is true of all experimental models? That's not true with their models if you're on a paid tier though, correct?

New comment by sauwan in "Mistral Small 3.1"

sauwan — Mon, 17 Mar 2025 22:11:47 +0000

Or Phi-4. Which seems to outperform it and be a smaller model from 4 months ago.