Hacker News: corlinp

New comment by corlinp in "Kimi K2.6: Advancing Open-Source Coding"

corlinp — Mon, 20 Apr 2026 18:22:21 +0000

Most of those inference providers are American, and China is actually at a disadvantage here because of export restrictions - US companies are using newer and more efficient chips.

New comment by corlinp in "Kimi K2.6: Advancing open-source coding"

corlinp — Mon, 20 Apr 2026 16:26:48 +0000

This should erase any doubt that AI Labs are making $$$ on API inference.

Kimi 2.5 (which this is based on) is served at $0.44 input / $2 output by a ton of different providers on OpenRouter, 2.6 will certainly be similar.

That's about 11X less than Opus for similar smarts.

New comment by corlinp in "Claude Opus 4.7"

corlinp — Thu, 16 Apr 2026 15:30:02 +0000

I'm running it for the first time and this is what the thinking looks like. Opus seems highly concerned about whether or not I'm asking it to develop malware.

> This is _, not malware. Continuing the brainstorming process.

> Not malware — standard _ code. Continuing exploration.

> Not malware. Let me check front-end components for _.

> Not malware. Checking validation code and _.

> Not malware.

New comment by corlinp in "Show HN: Ismcpdead.com – Live dashboard tracking MCP adoption and sentiment"

corlinp — Fri, 03 Apr 2026 23:16:36 +0000

IAM is generally binary (allowed yes/no) whereas MCP usually supports more nuance (always allow/ask if risky/always ask/no)

New comment by corlinp in "Tailscale's new macOS home"

corlinp — Fri, 03 Apr 2026 06:45:34 +0000

You'll have to get back to us with that name!

New comment by corlinp in "Tailscale's new macOS home"

corlinp — Fri, 03 Apr 2026 03:46:22 +0000

Well I suppose I can't miss out on the opportunity to plug my open-source menu bar app for voice-to-text in any app! Going on three years of development, believe it or not.

https://github.com/corlinp/voibe

New comment by corlinp in "Tailscale's new macOS home"

corlinp — Fri, 03 Apr 2026 00:12:37 +0000

When I set up a Mac I have a short list of things that I need to install. When I set up Windows I have a much longer list of things that I need to un-install. I much prefer the former.

New comment by corlinp in "Tailscale's new macOS home"

corlinp — Fri, 03 Apr 2026 00:10:42 +0000

iStat menus (or the new open source "Stats") is a brilliant use of the menu bar, but it can take a lot of space!

Then couple ordinary services that add menu bar icons that you don't even ask for (DropBox, Docker, Adobe, etc.) and you can overflow onto the notch quite quickly.

New comment by corlinp in "Tailscale's new macOS home"

corlinp — Thu, 02 Apr 2026 19:19:40 +0000

Every time I get a new Mac, I run these commands to reduce the spacing between menu bar icons. Lets you fit at least 2x the number of items in the menu bar.

```

defaults -currentHost write -globalDomain NSStatusItemSpacing -int 2

defaults -currentHost write -globalDomain NSStatusItemSelectionPadding -int 2

```

New comment by corlinp in "Cohere Transcribe: Speech Recognition"

corlinp — Tue, 31 Mar 2026 18:49:52 +0000

This is exactly the case today. Multimodal LLMs like gpt-4o-transcribe are way better than traditional ASR, not only because of deeper understanding but because of the ability to actually prompt it with your company's specific terminology, org chart, etc.

For example, if the prompt includes that Caitlin is an accountant and Kaitlyn is an engineer, if you transcribe "Tell Kaitlyn to review my PR" it will know who you're referring to. That's something WER doesn't really capture.

BTW, I built an open-source Mac tool for using gpt-4o-transcribe with an OpenAI API key and custom prompts: https://github.com/corlinp/voibe

New comment by corlinp in "Show HN: Free alternative to Wispr Flow, Superwhisper, and Monologue"

corlinp — Mon, 16 Feb 2026 23:35:14 +0000

I created Voibe which takes a slightly different direction and uses gpt-4o-transcribe with a configurable custom prompt to achieve maximum accuracy (much better than Whisper). Requires your own OpenAI API key.

https://github.com/corlinp/voibe

I do see the name has since been taken by a paid service... shame.

New comment by corlinp in "Ask HN: What are you working on? (October 2025)"

corlinp — Sun, 12 Oct 2025 21:18:32 +0000

Guessix is an LLM-powered word game like guess who!

We have a fun group working on it on Discord (find the discord invite in the How To)

https://guessix.com/

Success! You just installed the newest Google Toolbar

corlinp — Fri, 03 Oct 2025 05:42:38 +0000

Article URL: https://www.google.com/toolbar/ie/done.html

Comments URL: https://news.ycombinator.com/item?id=45459407

Points: 4

# Comments: 1

New comment by corlinp in "GPT-OSS Reinforcement Learning"

corlinp — Sat, 27 Sep 2025 16:12:56 +0000

Very interesting! Do the benchmarks hold up well or does it reduce performance in other areas too?

New comment by corlinp in "GPT-OSS Reinforcement Learning"

corlinp — Sat, 27 Sep 2025 16:11:27 +0000

Do you mean like structured outputs? Unfortunately here the model is guided to explicitly tell you when you violate the rules and why, it can confuse it's system rules with the game rules and say you're not allowed to ask a question about copyrighted material etc.

New comment by corlinp in "GPT-OSS Reinforcement Learning"

corlinp — Sat, 27 Sep 2025 06:56:34 +0000

The performance is great, but the censorship is ridiculous for me. I tried it as a backend for my game Guessix[1], but it would refuse for ridiculous reasons like "Cannot answer questions about copyrighted works like Harry Potter."

1. https://guessix.com/

New comment by corlinp in "Anthropic, Google, OpenAI and XAI Granted Up to $200M from Defense Department"

corlinp — Mon, 14 Jul 2025 23:08:04 +0000

Amazon has a number of foundation models under the name Amazon Nova, which they claimed were SOTA on release but I haven't heard much at all about them since.

New comment by corlinp in "Ask HN: Who is hiring? (June 2025)"

corlinp — Mon, 02 Jun 2025 16:34:47 +0000

ParaFi Capital | San Diego (Hybrid) | Sr. full-stack Engineer

ParaFi is a multi‑strategy investment and technology firm focused on the digital‑asset ecosystem. Since 2018 we’ve partnered with leading institutions to deploy venture, liquid, and quantitative capital. Our edge comes from marrying rigorous research, deep technical capability, and an operator’s mindset. We ship code, contribute to protocols, and build internal systems that keep us a step ahead of the market.

We’re looking for a senior engineer who can wear multiple hats - backend, frontend, data, and DevOps - to accelerate every part of ParaFi’s technology platform. You’ll design and own production systems that ingest billions of on‑chain and market datapoints, power quantitative strategies, and surface realtime insights to the investment team. Expect a high‑trust, low‑bureaucracy environment where your technical decisions directly influence portfolio returns.

To apply, send me an email directly and mention HN in the title. Just decode this email: iuxrot.v@vgxglo.ius

New comment by corlinp in "Ask HN: What are you working on? (May 2025)"

corlinp — Sun, 25 May 2025 20:51:36 +0000

Check out Voibe: https://github.com/corlinp/voibe

Open source Mac-native menu bar app for speech to text using GPT-4o-transcribe (current STT SOTA)

New comment by corlinp in "Suno v4.5"

corlinp — Sat, 03 May 2025 01:26:32 +0000

I used Suno to generate rap versions of Feynman's first lecture. It turned out really well!

https://suno.com/playlist/d2886382-bcb9-4d6d-8d7a-78625adcbe...