Hacker News: cjauvin

New comment by cjauvin in "Your intellectual fly is open when you use an LLM to author a post (2025)"

cjauvin — Sun, 06 Sep 2026 13:28:49 +0000

I think this is due to the fact that the language game that we have collectively decided to play, with AI, is not yet mature enough. In the language game of “giving a gift”, for instance, there is a distinction between giving a gift that you made yourself, and one that you bought at the store, but it is not that great, nobody cares a lot anymore. Right now, the language game of publishing words on the internet is strongly associated with the notion that these are “my words”, and the fact that they might have been written by a machine instead, introduces some discomfort. But it’s possible to imagine a future where this language game will have evolved enough that the notion of authorship by a particular machine entity, will not in itself be such an important issue, anymore.

New comment by cjauvin in "Discovery Loop"

cjauvin — Thu, 06 Aug 2026 00:03:54 +0000

LawZero, Yoshua Bengio’s startup, also proposes to automate scientific research and experimentation, from the perspective of safety, by being explicitly “non-agentic”:

https://lawzero.org/en/publication/scientist-ai-safe-design-...

What does it mean to create with AI?

cjauvin — Fri, 10 Apr 2026 15:11:17 +0000

Article URL: https://cjauvin.github.io/posts/creating-with-ai/

Comments URL: https://news.ycombinator.com/item?id=47719351

Points: 1

# Comments: 0

New comment by cjauvin in "Show HN: 41 years sea surface temperature anomalies"

cjauvin — Thu, 09 Apr 2026 13:55:44 +0000

For those interested in this type of climate data visualization apps, I have worked on this one in the past, which is actively maintained with a lot of love, and very nice:

https://portraits.ouranos.ca/en

Conveying math intuition is hard

cjauvin — Sun, 08 Mar 2026 15:38:40 +0000

Article URL: https://cjauvin.github.io/posts/conveying-math-intuition-is-hard/

Comments URL: https://news.ycombinator.com/item?id=47298191

Points: 2

# Comments: 0

Does ChatGPT know what is a question?

cjauvin — Tue, 24 Feb 2026 17:13:21 +0000

Article URL: https://cjauvin.github.io/posts/llm-question-answering/

Comments URL: https://news.ycombinator.com/item?id=47139645

Points: 1

# Comments: 0

New comment by cjauvin in "Six Math Essentials"

cjauvin — Sun, 22 Feb 2026 23:35:46 +0000

Sorry for the stupid question but is Elliptic Tales your favorite or is it Summing it up?

New comment by cjauvin in "A sane but bull case on Clawdbot / OpenClaw"

cjauvin — Wed, 04 Feb 2026 15:58:20 +0000

For "something that is published" (which includes a comment like this) I clearly dislike it too, but for chatting / texting, I realize that I often use it more than my interlocutors, and I'm not sure why. There's a part of lazyness I guess, but also a vague sense of "conveying the impression of a never ending stream of communication", which is closer in my mind to the essence of the chat medium. In French, there is also the additional layer of "using the accents or not".

New comment by cjauvin in "Show HN: I wrapped the Zorks with an LLM"

cjauvin — Tue, 27 Jan 2026 21:38:21 +0000

Very interesting project! I cannot resist mentioning an old project of mine that was made in a very similar spirit, but way before any LLM: wrapping a classic Lone Wolf gamebook around a very crude text parser: https://projectaon.org/staff/christian/gamebook.js

I had written an entire "framework" for it, in JS (so in theory more books could be supported), but it never went anywhere: https://github.com/cjauvin/gamebook.js

The Sexual Paradise that never was

cjauvin — Thu, 01 Jan 2026 16:01:13 +0000

Article URL: https://quillette.com/2025/12/30/the-sexual-paradise-that-never-was-margaret-mead-samoa/

Comments URL: https://news.ycombinator.com/item?id=46455083

Points: 4

# Comments: 2

Insurmountable Hans (or the era of turbocharged goalpost moving)

cjauvin — Sun, 14 Dec 2025 15:03:36 +0000

Article URL: https://cjauvin.github.io/posts/insurmountable-hans/

Comments URL: https://news.ycombinator.com/item?id=46263524

Points: 2

# Comments: 0

Some models of reality are bolder than others

cjauvin — Tue, 02 Dec 2025 15:23:57 +0000

Article URL: https://cjauvin.github.io/posts/metaphysical-boldness/

Comments URL: https://news.ycombinator.com/item?id=46122114

Points: 24

# Comments: 18

New comment by cjauvin in "Await Is Not a Context Switch: Understanding Python's Coroutines vs. Tasks"

cjauvin — Wed, 26 Nov 2025 13:26:34 +0000

I asked a question about exactly this on Stack Overflow, many years ago, which I think received a nice answer: https://stackoverflow.com/questions/57966935/asyncio-task-vs...

Manifesto: AI (as a term and field) should subsume CS

cjauvin — Tue, 25 Nov 2025 16:25:23 +0000

Article URL: https://cjauvin.github.io/posts/cs-should-become-ai/

Comments URL: https://news.ycombinator.com/item?id=46047391

Points: 2

# Comments: 2

We didn't get the AI failure modes that philosophy anticipated

cjauvin — Sun, 23 Nov 2025 15:02:26 +0000

Article URL: https://cjauvin.github.io/posts/ai-failure-mode/

Comments URL: https://news.ycombinator.com/item?id=46024057

Points: 2

# Comments: 0

Proof of Prompt

cjauvin — Sat, 25 Oct 2025 15:09:12 +0000

Article URL: https://cjauvin.github.io/posts/proof-of-prompt/

Comments URL: https://news.ycombinator.com/item?id=45704473

Points: 1

# Comments: 0

New comment by cjauvin in "Learning Persian with Anki, ChatGPT and YouTube"

cjauvin — Wed, 24 Sep 2025 16:39:26 +0000

Author here: my learning objectives, in order of importance, are: (1) vocal understanding, (2) speaking, (3) reading, and (4) typing and writing (far further). As I explain, I'm mostly bypassing the problem of typing by using screenshots (ChatGPT's OCR capabilities are very good, and Anki works very well with it too).

Learning Persian with Anki, ChatGPT and YouTube

cjauvin — Wed, 24 Sep 2025 12:45:07 +0000

Article URL: https://cjauvin.github.io/posts/learning-persian/

Comments URL: https://news.ycombinator.com/item?id=45359524

Points: 265

# Comments: 90

New comment by cjauvin in "We Politely Insist: Your LLM Must Learn the Persian Art of Taarof"

cjauvin — Tue, 23 Sep 2025 13:59:28 +0000

Thanks for suggesting it, here you go: https://cjauvin.github.io/posts/learning-persian/

New comment by cjauvin in "We Politely Insist: Your LLM Must Learn the Persian Art of Taarof"

cjauvin — Mon, 22 Sep 2025 12:15:00 +0000

I've been using ChatGPT to learn Persian (as a third language) for more than a year now (along with a heavy use of Anki), and it's incredibly useful and surprisingly good, for about everything: romanization, OCR from screenshots, deep explanations of complex and subtle stuff, etc.