Hacker News: arisAlexis

The Abundance Paradox

arisAlexis — Sun, 20 Sep 2026 10:31:25 +0000

Article URL: https://kshaped.substack.com/p/the-abundance-paradox

Comments URL: https://news.ycombinator.com/item?id=49774431

Points: 3

# Comments: 1

New comment by arisAlexis in "Finder is so frustrating and has been since day one"

arisAlexis — Sun, 06 Sep 2026 19:29:02 +0000

Recently switched to Mac and I always have this question mark like how can this be so bad after decades and why is everyone cool with it

Tell HN: Use AI to music score your books

arisAlexis — Tue, 18 Aug 2026 10:34:44 +0000

Not many people read books but AI is under rated for the ability to theme your experience. If you ask Gemini to create a youtube music playlist for you for a specific book the result is amazing and I wanted to share this with others because it changed my book reading to an actual audio visual experience.

There are some apps that do that but the songs are not on point, too "theme like". Gemini can find real songs that are a super fit.

Comments URL: https://news.ycombinator.com/item?id=49343693

Points: 1

# Comments: 0

New comment by arisAlexis in "Grok Bot"

arisAlexis — Thu, 13 Aug 2026 15:48:39 +0000

What troubles you in the meaning?

New comment by arisAlexis in "Grok Bot"

arisAlexis — Wed, 12 Aug 2026 08:42:52 +0000

I hope some relative of yours gets saved and cured by a disease that LLMs cured and that will change your mind forever

New comment by arisAlexis in "Why Wall Street is ignoring big tech's debt [video]"

arisAlexis — Sun, 09 Aug 2026 18:44:10 +0000

Yes and since there is no fraud there is no reason for this panic they know what they are doing

New comment by arisAlexis in "Why Wall Street is ignoring big tech's debt [video]"

arisAlexis — Sun, 09 Aug 2026 14:49:32 +0000

Capitalism works with debt for growth. Strange HN doesn't understand this

New comment by arisAlexis in "AI Mania: From Tulips to Tokens"

arisAlexis — Sun, 02 Aug 2026 22:16:29 +0000

In the meantime tulips prove math theorems that humans couldn't solve. Ridiculous article title (I wouldn't read it)

New comment by arisAlexis in "Apple Will 'Watch Everything Burn' When AI Bubble Bursts"

arisAlexis — Sat, 01 Aug 2026 08:18:46 +0000

Electricity and computers can't solve new math and physics nor make us immortal and drive humanity to the next step.

New comment by arisAlexis in "Apple Will 'Watch Everything Burn' When AI Bubble Bursts"

arisAlexis — Sat, 01 Aug 2026 08:05:59 +0000

Almost all Nobel laureates of AI disagree with you but ok I get what you are saying

New comment by arisAlexis in "Apple Will 'Watch Everything Burn' When AI Bubble Bursts"

arisAlexis — Fri, 31 Jul 2026 21:28:10 +0000

Stock valuation has nothing to do with AI being the most transformational tech ever devised. Like who can't grasp that

New comment by arisAlexis in "GPT-5.6 vs. Claude Fable 5 for Physical AI, which performs best?"

arisAlexis — Wed, 29 Jul 2026 18:09:17 +0000

Google with apptronic should have good models soon

New comment by arisAlexis in "Show HN: Echologue – the private AI voice journal I built for myself"

arisAlexis — Wed, 29 Jul 2026 14:04:57 +0000

the best would be on device inference only but we need maybe 6 months for a small model to match capabilities yet. I wanted to do it like that but even my pixel 10 suffered.

New comment by arisAlexis in "Show HN: Echologue – the private AI voice journal I built for myself"

arisAlexis — Wed, 29 Jul 2026 13:47:20 +0000

1) the app is using a database stored on your phone. you can export it all in json or llm format. the one is for export/import and the other to feed an LLM with your data to chat more

2) yes I tried it and it becomes so slow it's unworkable right now but in a future version totally possible. Gemma 4 needs an iphone 17 pro or similar to run in a normal timeframe and still it's slow and also the whisper-large is also very slow. it would also need to download some gigs of data. but that was actually the first version I built :)

New comment by arisAlexis in "Show HN: Echologue – the private AI voice journal I built for myself"

arisAlexis — Wed, 29 Jul 2026 13:41:36 +0000

I did consider it at one point the problem is that the prompt and instruction following for formating and extracting tags, nouns etc and the json returns are unreliable if you switch models and especially if it's an older model. right now i'm using Gemma 4 and works smoothly so it would need to be BYOK for gemma only which is doable. If more people ask I could do it sure.

Show HN: Echologue – the private AI voice journal I built for myself

arisAlexis — Wed, 29 Jul 2026 12:43:36 +0000

I have tried journaling many times but nothing stuck. So I decided to make my own app for myself with these features:

* Voice first

* Private first

* AI chat

* Automatic tagging, meaning extraction, and semantic retrieval using embeddings stored locally

* Export to LLM

the AI angle is especially interesting for me. It allows me to ask questions like:

* "remind me highlights and crazy nights in the last 3 months"

* "How was I feeling during my trip in Spain and how big of a problem was my breakup"

* "How would you judge my overall interactions with Marc after I told him about my problems"

the overall process is fire and forget. I just talk for let's say a minute every day or when there was something of interest.

Everything is stored on device. The AI inference is done with Zero Data Retention Endpoints. No email or anything else is kept, you are completely anonymous, I have no idea what or how people use this.

Otherwise journaling doesn't work. I can't say my secret thoughts when I know someone has a master key or can suffer a security breach.

I hope you enjoy the product as much as I do.

Comments URL: https://news.ycombinator.com/item?id=49096767

Points: 29

# Comments: 13

New comment by arisAlexis in "How Do We Stop Vibe Coding?"

arisAlexis — Fri, 24 Jul 2026 13:50:10 +0000

We can also go back to the telegraph

New comment by arisAlexis in "OpenAI and Hugging Face address security incident during model evaluation"

arisAlexis — Wed, 22 Jul 2026 07:35:17 +0000

why laugh? this is one of the most well known studied possibilities in the AI alignment field, maybe you are unaware of this field.

New comment by arisAlexis in "OpenAI and Hugging Face address security incident during model evaluation"

arisAlexis — Tue, 21 Jul 2026 21:44:30 +0000

They said: AI is becoming dangerously autonomous and capable. Proof of today's breach. Crowd "hey why didn't you say so, c'mon it's marketing". Them "we said so".

New comment by arisAlexis in "OpenAI and Hugging Face address security incident during model evaluation"

arisAlexis — Tue, 21 Jul 2026 21:43:20 +0000

About their creation? Yes as most of inventors about their invention usually