Hacker News: jari_mustonen

New comment by jari_mustonen in "F-15E jet shot down over Iran"

jari_mustonen — Fri, 03 Apr 2026 19:51:24 +0000

[flagged]

New comment by jari_mustonen in "LLM Writing Tropes.md"

jari_mustonen — Mon, 09 Mar 2026 10:07:26 +0000

Some of these are neccesary parts of LLM's. They use the content they create to direct what they are going to say. This applies to patterns like "In conclusion, ..." and what the author calls "Fractal summary". Turn them off, and the general quality of the AI thought gets lower.

New comment by jari_mustonen in "The United States and Israel have launched a major attack on Iran"

jari_mustonen — Sat, 28 Feb 2026 14:16:14 +0000

There is nothing ideal about that outcome. The "regime change" people talk about is intended to look like what happened in Libya: A failed state that falls in anarchy.

Don't Add AI to Your App – Add Your App to AI

jari_mustonen — Sun, 15 Feb 2026 18:31:32 +0000

Article URL: https://maalla.dev/posts/dont-add-ai-to-your-app/

Comments URL: https://news.ycombinator.com/item?id=47026095

Points: 3

# Comments: 0

Death of the Certified Expert

jari_mustonen — Sun, 15 Feb 2026 18:29:39 +0000

Article URL: https://maalla.dev/posts/death-of-the-certified-expert/

Comments URL: https://news.ycombinator.com/item?id=47026068

Points: 2

# Comments: 0

Biases in the Blind Spot: Detecting What LLMs Fail to Mention

jari_mustonen — Thu, 12 Feb 2026 14:00:28 +0000

Article URL: https://arxiv.org/abs/2602.10117

Comments URL: https://news.ycombinator.com/item?id=46988925

Points: 1

# Comments: 0

New comment by jari_mustonen in "Problems with C++ exceptions"

jari_mustonen — Wed, 12 Nov 2025 06:29:44 +0000

The classic "Frequently Questioned Answers" is the ultimate takedown of this abomination of a language.

https://yosefk.com/c++fqa/

New comment by jari_mustonen in "Delete FROM users WHERE location = 'Iran';"

jari_mustonen — Wed, 24 Sep 2025 05:43:44 +0000

There are sexual predators that do pray on men and the sadistic types probably find their way to prison guards.

New comment by jari_mustonen in "Want to piss off your IT department? Are the links not malicious looking enough?"

jari_mustonen — Fri, 19 Sep 2025 06:24:21 +0000

Stuff like this is good for infinite loops: https://gonephishing.me/shell-jacker/shell-jacker/worm_launc...

New comment by jari_mustonen in "Chrome's New AI Features"

jari_mustonen — Thu, 18 Sep 2025 17:27:09 +0000

So they integrate Gemini to summarize open web pages and consolidate all your open tabs into summaries. (Open lot's of pages, then summarize them all.) You can search your history with natural language and type Gemini queries directly into the address bar.

This will give them a cognitive profile of you: reading comprehension, decision-making patterns, knowledge gaps, etc.

Scary.

New comment by jari_mustonen in "Chrome: The browser you love, reimagined with AI"

jari_mustonen — Thu, 18 Sep 2025 17:26:21 +0000

So they integrate Gemini to summarize open web pages and consolidate all your open tabs into summaries. You can search your history with natural language and type Gemini queries directly into the address bar.

this will give them a cognitive profile of you: reading comprehension, decision-making patterns, knowledge gaps, etc.

Scary.

New comment by jari_mustonen in "Tau² benchmark: How a prompt rewrite boosted GPT-5-mini by 22%"

jari_mustonen — Wed, 17 Sep 2025 14:01:44 +0000

Here is the summary of key improvements made:

1. Structure & Flow

    - Decision Trees: Clear branching logic with ├── and └── notation

    - Sequential Steps: Numbered, ordered procedures instead of scattered explanations

    - Prerequisites: Explicit dependency checks before proceeding

2. AI Agent Optimizations

    - Tool Call Clarity: Exact function names and parameters

    - Binary Decisions: Clear yes/no conditions instead of ambiguous language

    - Error Handling: Specific failure conditions and next steps

    - Verification Steps: "Recheck" instructions after each fix

3. Cognitive Load Reduction

    - Reference Tables: Quick lookup for tools and purposes

    - Pattern Recognition: Common issue combinations and their solutions

    - Critical Reminders: Common AI mistakes section to prevent errors

4. Actionable Language

    - Removed verbose explanations mixed with instructions

    - Consolidated multiple documents' logic into single workflows 

    - Used imperative commands: "Check X", "If Y then Z"

    - Added immediate verification steps

New comment by jari_mustonen in "Gemini 2.5 Flash Image"

jari_mustonen — Wed, 27 Aug 2025 04:37:47 +0000

Is it capable of generating white males?

Given that this has been a serious problem with Google models, I would guess it would have been a good thing to at least add one such example in the marketing material. If the marketing material is to be believed, the model really prefers black females.

When asked what model it is, GTP-5 says it's GPT-4.5

jari_mustonen — Fri, 08 Aug 2025 10:40:28 +0000

Here's the full dialogue:

Q: What model are you?

A: I’m based on the GPT-4.5 architecture, running in the ChatGPT environment with reasoning and coding capabilities.

Comments URL: https://news.ycombinator.com/item?id=44835501

Points: 2

# Comments: 2

New comment by jari_mustonen in "Open models by OpenAI"

jari_mustonen — Wed, 06 Aug 2025 09:09:09 +0000

It's the political bias in the training material. No surprise there.

New comment by jari_mustonen in "Show HN: MCP server that lets Claude Code consult other LLMs"

jari_mustonen — Mon, 28 Jul 2025 12:07:29 +0000

This is really useful for Claude Code. The second opinion is often really insightful. Also, in a lot of cases, when CC can't fix a bug, Gemini can.

New comment by jari_mustonen in "The behavior of LLMs in hiring decisions: Systemic biases in candidate selection"

jari_mustonen — Tue, 20 May 2025 15:56:04 +0000

I think the problem is that removing factors like name, gender, or marital status does not truly make the process unbiased. These factors are only sources of bias if there is no correlation between, for example, marital status and the ability to work or some secondary characteristic that is preferable to employer such as loyalty. It can be easily hypothesized that marital status might stabilize a person or make them more likely to stay with one employer, or other traits that are preferable.

Similar examples can also be made for name and gender.

New comment by jari_mustonen in "The behavior of LLMs in hiring decisions: Systemic biases in candidate selection"

jari_mustonen — Tue, 20 May 2025 12:06:41 +0000

The gender bias is not primarily about LLMs but rather a reflection of the training material, which mirrors our culture. This is evident as the bias remains fairly consistent across different models.

The bias toward the first presented candidate is interesting. The effect size for this bias is larger, and while it is generally consistent across models, there is an exception: Gemini 2.0.

If things in the beginning of the prompt are considered "better", does this affect chat like interface where LLM would "weight" first messages to be more important? For example, I have some experience with Aider, where LLM seems to prefer the first version of a file that it has seen.

New comment by jari_mustonen in "YouTube announces Gemini AI feature to target ads when viewers are most engaged"

jari_mustonen — Thu, 15 May 2025 13:38:17 +0000

Of course, AI will be used, first and foremost, to push advertising messages.

Is it just me, or do others also wish they could use public transportation, go for a walk in a park, or watch an educational video without being constantly bombarded with ads at every turn?

If there’s a jurisdiction that has an environmental protection tax on display advertising, whether in the real world or online, let me know. I’ll be the first to move there.

New comment by jari_mustonen in "Our narrative prison"

jari_mustonen — Wed, 14 May 2025 17:41:23 +0000

The article mentions Jung's "collective unconscious," which is often misunderstood.

What he meant by it is that some unconscious features are collective, meaning they are genetically programmed in all people. Jung believed this also includes certain thought patterns, which can be inferred from stories. For example, he would have argued that a paragon of wisdom is typically an older man with a white beard (Gandalf and Dumbledore come to mind) because we have a genetically programmed inclination to see older men with white beards as paragons of wisdom.

Jung liked to use these kinds of methods to analyze the human psyche and its structures. Interesting guy. If anyone is interested, I recommend his collection of essays, Modern Man in Search of a Soul, as a first read.