Hacker News: killermouse0

New comment by killermouse0 in "MAI-Code-1-Flash"

killermouse0 — Tue, 02 Jun 2026 19:40:50 +0000

I was wondering the same. I guess it makes sense to use a heavy weight model to make the entire design and split the work so that smaller models (possibly local one?) would then do the coding... But how would I even do that? I'm using Claude Code. Would I need support for this within the harness ?

New comment by killermouse0 in "Living human brain cells play DOOM on a CL1 [video]"

killermouse0 — Mon, 09 Mar 2026 07:17:05 +0000

Born in 1979 but I don't get it. What is it about?

When the Assistant Becomes the Attacker: Hidden Risks of Tool-Enabled LLMs

killermouse0 — Sun, 08 Jun 2025 18:36:52 +0000

Article URL: https://www.sakana.fr/blog/2025-06-08-llm-hidden-risks/

Comments URL: https://news.ycombinator.com/item?id=44218756

Points: 2

# Comments: 0

New comment by killermouse0 in "Show HN: How good is your color vision? Find out in my new game"

killermouse0 — Wed, 05 Feb 2025 19:57:55 +0000

Wrong post?

New comment by killermouse0 in "Can LLMs accurately recall the Bible?"

killermouse0 — Mon, 30 Dec 2024 09:42:46 +0000

I believe I saw or read somewhere that, in the case of the brain, memories were not as much stored as they were reconstructed when recalled. If that's true, I feel like we are witnessing something similar with LLMs as well as with stable diffusion type of things. Is there any studies looking into this in the AI world? Also if anyone knows what I'm referring to (i.e "reconstructing memories") I would love some pointers because I can't remember for the love of me where I heard or read of this idea!

New comment by killermouse0 in "Ollama releases Python and JavaScript Libraries"

killermouse0 — Thu, 25 Jan 2024 07:31:03 +0000

Would you share that code? I'm not familiar with using the mic in Linux, but interested to do something similar!

New comment by killermouse0 in "Core War, a very old game about programming"

killermouse0 — Mon, 14 Aug 2023 07:48:16 +0000

Did you study at the EPITA by any chance? That was one of my favorite coding assignment during my time there!

Ask HN: Selectively Refusing Anonymous Interactions?

killermouse0 — Fri, 30 Dec 2022 08:20:46 +0000

I appreciate the freedom of speech that anonymity on the internet can allow. However, for content creators for example, I can see the value in engaging only with people who have provided their real identity, perhaps through a KYC process, mainly to reduce spam and increase safety.

Do you think social media platforms should allow you to require this level of identity verification, possibly through a checkbox like "accessible only to people who have completed KYC". Assuming this would be backed by regulations of some sort?

Comments URL: https://news.ycombinator.com/item?id=34183073

Points: 1

# Comments: 2

New comment by killermouse0 in "Show HN: Bionic Reading – Formats text to make it faster to read"

killermouse0 — Fri, 25 Mar 2022 11:20:59 +0000

Is there a Chrome or Firefox browser add-on?

New comment by killermouse0 in "Trials begin on lozenge that rebuilds tooth enamel"

killermouse0 — Sat, 29 May 2021 22:38:35 +0000

Would you care to elaborate on those diet changes?

Ask HN: Pointers for a news recommender project?

killermouse0 — Wed, 23 May 2018 08:52:57 +0000

Hey HN,

I'm getting started with a little project to practice my nascent machine learning skills.

The idea is to have users list a few websites they like and then, based on those, suggest a few interesting news as they get posted. The news will be delivered by email. I want it to be privacy focused.

So, I already know this is not really original. This is really more a learning project than anything.

The "battle plan" so far is: 1. Build a landing page where people can subscribe and list their favorite news sources, with a few tags. Trying to "crowd source" the effort of finding content and cataloging 2. Drive traffic to the landing page somehow. I was going to check AdWords campaigns but they seem too pricey for something which is basically for fun more than profit. I'll try to rely on social discussions / comments. Any other suggestion on this would be appreciated! 3. Ship an periodic email with 5 links or such, which are supposedly interesting / have the email include links to "thumb up / down" the content, to further customize the recommending engine 4. If there's any visible interest and / or if providing it starts costing me more than I'm willing to pay, I'll attempt to monetize it. For example by adding sponsored content / or advertising maybe?

What I want to gain from this test is: 1/ Practice machine learning 2/ Form some habits that will help me shipping other side projects in the future 3/ Practice other skills such as SEO, Cloud architectures (aiming at the most serverless architecture I can imagine. Right now the landing page is hosted on S3+CloudFront, the form is a Google Form (yes, that one looks cheap))

I would love to hear your thoughts about this all. Any suggestion?

The landing page is here: http://newspulse.ai Feel free to comment on it, and to fill the form (with a fake email if you don't want to hear about it again!), that will kickstart my news source catalog.

Thanks for any help!

Comments URL: https://news.ycombinator.com/item?id=17132399

Points: 3

# Comments: 1

New comment by killermouse0 in "Where’s all my CPU and memory gone? The answer: Slack"

killermouse0 — Thu, 27 Jul 2017 21:17:58 +0000

Why don't you guys use rambox? It basically loads slack's web interface in the client. And it supports a plethora of instant messaging services. Never had any issue with performance.

Elasticsearch tuning: use case with Bitcoin exchange rate collection

killermouse0 — Mon, 13 Mar 2017 14:39:29 +0000

Article URL: https://linkbynet.github.io/elasticsearch/tuning/2017/02/07/Bitcoin-ELK-NiFi.html

Comments URL: https://news.ycombinator.com/item?id=13858134

Points: 1

# Comments: 0