Hacker News: haffi112

New comment by haffi112 in "Why are large language models so terrible at video games?"

haffi112 — Mon, 01 Jun 2026 11:43:33 +0000

They are also pretty bad at navigating mazes (which can be somewhat similar in spirit to text adventures where you need to navigate through text): https://arxiv.org/abs/2507.20395

Turning recorded D&D sessions into comics

haffi112 — Thu, 14 May 2026 16:00:37 +0000

Article URL: https://haffi112.github.io/2026/05/14/dnd-comics/

Comments URL: https://news.ycombinator.com/item?id=48137314

Points: 3

# Comments: 0

New comment by haffi112 in "Habitual coffee intake shapes the microbiome, modifies physiology and cognition"

haffi112 — Sat, 25 Apr 2026 08:20:05 +0000

I stopped drinking coffee for four or five years. I drank a lot before. You do realise that it has a strong psychoactive effect, at least it did for me.

I still don't drink coffee, but I started experimenting with paraxanthine and I absolutely love it (paraxanthine is the primary metabolite of caffeine and is also a stimulant). I feel like it gives me most of the benefit of caffeine with very few downsides (no jitters, no crash, exits your system faster).

New comment by haffi112 in "Semantic ablation: Why AI writing is generic and boring"

haffi112 — Wed, 18 Feb 2026 09:39:52 +0000

Oh the irony, I also felt that way when I started reading it. It borders on being hypocrisy given the topic of the article.

New comment by haffi112 in "Skills Officially Comes to Codex"

haffi112 — Sat, 20 Dec 2025 11:00:57 +0000

What are your favourite skills?

New comment by haffi112 in "[dead]"

haffi112 — Wed, 12 Nov 2025 09:34:22 +0000

You can find a demo here: https://huggingface.co/spaces/facebook/omniasr-transcription...

New comment by haffi112 in "Artificial Writing and Automated Detection [pdf]"

haffi112 — Mon, 27 Oct 2025 18:53:46 +0000

Even if it was close to being near perfect, that is still not enough due to the negative impact of false positive detections on students.

New comment by haffi112 in "Artificial Writing and Automated Detection [pdf]"

haffi112 — Mon, 27 Oct 2025 18:52:06 +0000

That's where the humanizers come in. These are solutions that take LLM generated text and make it sound human written to avoid detection.

The principle of training them is quite simple. Take an LLM and reward it for revising text so that it doesn't get detected. Reinforcement learning takes care of the rest for you.

New comment by haffi112 in "Vibe coding has turned senior devs into 'AI babysitters'"

haffi112 — Sun, 14 Sep 2025 21:07:30 +0000

Why do the news need to make everything sound sensational. Let's move on.

New comment by haffi112 in "Cognitive load is what matters"

haffi112 — Sat, 30 Aug 2025 18:23:33 +0000

The section on nested ifs reminded be of being a Nevernester: https://www.youtube.com/watch?v=CFRhGnuXG-4 (it's a short [~8 min], fun watch)

New comment by haffi112 in "GPT-5"

haffi112 — Thu, 07 Aug 2025 17:28:25 +0000

It makes it look like the presentation is rushed or made last minute. Really bad to see this as the first plot in the whole presentation. Also, I would have loved to see comparisons with Opus 4.1.

Edit: Opus 4.1 scores 74.5% (https://www.anthropic.com/news/claude-opus-4-1). This makes it sound like Anthropic released the upgrade to still be the leader on this important benchmark.

New comment by haffi112 in "Springer Nature book on machine learning is full of made-up citations"

haffi112 — Wed, 09 Jul 2025 08:51:48 +0000

You would think that Springer did the due diligence here, but what is the value of a brand such as Springer if they let these AI slops through their cracks?

This is an opportunity for brands to sell verifiability, i.e., that the content they are selling has been properly vetted, which was obviously not the case here.

New comment by haffi112 in "Energy drinks linked to rise in colorectal and blood cancer"

haffi112 — Sat, 17 May 2025 16:53:41 +0000

Taurine deficiency has been claimed to be a driver of aging [1]. The claim from the news article about it possibly being related to cancer seems like it needs a much stronger justification.

[1] https://www.science.org/doi/10.1126/science.abn9257

New comment by haffi112 in "A Research Preview of Codex"

haffi112 — Fri, 16 May 2025 15:13:12 +0000

(watching live) I'm wondering how it performs on the METR benchmark (https://metr.org/blog/2025-03-19-measuring-ai-ability-to-com...).

New comment by haffi112 in "Ask HN: Is Cursor deleting working code for you too or is it just me?"

haffi112 — Sat, 08 Mar 2025 12:03:33 +0000

It has happened to me on very large files and when you've had a long composer session. I usually check every file that is being modified for large removals because of this. It's a bit annoying, but something I can tolerate.

New comment by haffi112 in "Higher potassium intake at dinner linked to fewer sleep disturbances – study"

haffi112 — Sat, 18 Jan 2025 09:19:08 +0000

The original website is a news report of an article. The one he posted is from a peer-reviewed journal which has a much higher standard of reporting. The information there is reported by scientists with expertise in the field. You cannot expect the same level of rigour from journalists that try to sensationalise findings to get more clicks.

New comment by haffi112 in "Cognitive load is what matters"

haffi112 — Thu, 26 Dec 2024 10:17:16 +0000

This post reminded me of Nevernesting: https://www.youtube.com/watch?v=CFRhGnuXG-4

New comment by haffi112 in "Ask HN: What are you working on? (October 2024)"

haffi112 — Mon, 28 Oct 2024 13:30:22 +0000

Looking forward to see that project on air quality.

AI Ethics Survey: Where Do You Stand on the Future of Intelligence?

haffi112 — Wed, 02 Oct 2024 17:47:09 +0000

Article URL: http://www.aiethics.is/

Comments URL: https://news.ycombinator.com/item?id=41723187

Points: 1

# Comments: 0

New comment by haffi112 in "X becoming a 'ghost town' of bots as AI-generated spam content floods internet"

haffi112 — Wed, 28 Feb 2024 14:17:16 +0000

For what I follow, it looks genuine.

However, for many viral posts, many of the responses have nothing to do with the original post. It looks like bots/users that are riding off of the success of the viral post in an attempt to get more views/likes/followers. It's a sad behaviour that lessens the experience of the platform.