Hacker News: dingocat

New comment by dingocat in "Qwen3.6-Max-Preview: Smarter, Sharper, Still Evolving"

dingocat — Mon, 20 Apr 2026 18:22:26 +0000

Yet.

New comment by dingocat in "It's insulting to read AI-generated blog posts"

dingocat — Mon, 27 Oct 2025 17:48:50 +0000

> “Blog” stands for “web log”. If it’s on the web, it’s digital, there was never a period when blogs were hand written.

Did you use AI to write this...? Because it does not follow from the post you're replying to.

New comment by dingocat in "Llama.cpp supports Vulkan. why doesn't Ollama?"

dingocat — Sat, 01 Feb 2025 07:58:39 +0000

Which you have to go to the model page to find.

New comment by dingocat in "Llama.cpp supports Vulkan. why doesn't Ollama?"

dingocat — Fri, 31 Jan 2025 16:09:19 +0000

And their documentation makes that distinction clear, having dedicated a section specifically to the distilled models.

New comment by dingocat in "Llama.cpp supports Vulkan. why doesn't Ollama?"

dingocat — Fri, 31 Jan 2025 15:56:24 +0000

A distinction they make clear and write extensively about on the model page, yes?

New comment by dingocat in "Llama.cpp supports Vulkan. why doesn't Ollama?"

dingocat — Fri, 31 Jan 2025 14:02:45 +0000

What do you mean there is no such thing as R1-1.5b? DeepSeek released a distilled version based on a 1.5B Qwen model with the full name DeepSeek-R1-Distill-Qwen-1.5B, see chapter 3.2 on page 14 of their research article [0].

[0] https://arxiv.org/abs/2501.12948

New comment by dingocat in "Ask HN: How is your job search going?"

dingocat — Fri, 03 Jan 2025 03:11:45 +0000

It hasn't been great. Applying for jobs in this market while having the post-MSc burnout has been tough. I finished an MSC in AI back in June, but there are so few AI-relevant jobs where I live it's depressing. I've interview for data science and analyst roles, but barely get in the door.

I'm getting a good amount of interviews for developer and data engineering positions, but the competition is tough. Many positions have seen a 5x increase in candidates since the same time last year, according to my interviewers.

However, I'm hopefully getting an offer as a data platform engineer soon. The department leader has ranked me as their first choice, so unless the higher-ups complain... Knock on wood.

New comment by dingocat in "A GPT-4 capability forecasting challenge"

dingocat — Sat, 02 Sep 2023 13:12:52 +0000

I have multiple questions regarding the methods of this test.

The biggest one is that, well... The test doesn't aim to see what GPT-4 can do and how well it does it, only whether the participant can guess the (possibly cherry-picked) answer the author decided on. In short, we don't know if he sampled answers and decided on the most probable answer (akin to consensus voting/self-consistency[1]), or if he asked a question and chose the first one.

Maybe GPT-4 guesses the correct answer for a question 80% of the time, but he got unlucky? You don't know, the author doesn't tell you. The answers are generated ahead of time and are the same every time you go through the test.

[1] https://doi.org/10.48550/arXiv.2203.11171

New comment by dingocat in "How to edit your own lousy writing (2017)"

dingocat — Sat, 02 Sep 2023 12:44:00 +0000

A few pages? You barely need a single sentence. "Build lasting habits by recognizing how triggers lead to action."

New comment by dingocat in "Man can change his pupil size on command"

dingocat — Wed, 01 Sep 2021 13:24:10 +0000

Ditto, I can do it as well. I can best describe it as looking at an object and shifting it in/out of focus.