Hacker News: aledevv

New comment by aledevv in "Writing by hand is good for your brain"

aledevv — Thu, 23 Jul 2026 15:46:27 +0000

> when you write things down by hand you’re recruiting more of your brain, which is a good thing.

I completely agree! Perhaps it's simply for one reason: slowness.

Writing by hand slows down and the brain "breathes", calms down, and the waves of thought flow at their proper pace.

We aren't made to rush always: by slowing down, our brain also has time to better process thoughts and information, one at a time, and each one is given the "time it deserves."

Our brain works best when it's relaxed and has time to make all its connections.

Thinking is, first and foremost, an exercise in slowness.

(ps: I'm also left-handed, I wonder if this also affects the functioning of the brain...).

New comment by aledevv in "Show HN: LongTerMemory Study tool with no subscription built with QDrant and RAG"

aledevv — Tue, 21 Jul 2026 16:52:08 +0000

Yes, I do semantic chunk to better split the text into coherent chunks. I even use Llamaparse api (by Llamaindex) to parsing any type of documents, images or imported study material, with a very high quality results. Llamaparse is great!

Show HN: LongTerMemory Study tool with no subscription built with QDrant and RAG

aledevv — Tue, 21 Jul 2026 08:44:46 +0000

After trying out various study tools, I decided to create my own.

I wanted a quick and simple way to upload any study material, have the app generate questions, and then set up a daily review schedule.

So, I built it by creating a RAG system and a scheduler to trigger the daily review sessions.

Comments URL: https://news.ycombinator.com/item?id=48989705

Points: 1

# Comments: 2

New comment by aledevv in "The Future Worth Building Is Human"

aledevv — Tue, 14 Jul 2026 12:50:38 +0000

> Artificial intelligence can do more every day, but deciding what it should do is up to us

> For artificial intelligence to benefit from distributed knowledge, it must itself be distributed.

I wish to highlight these two important concepts, with which I fully agree.

Artificial intelligence must enable all of humanity to excel and realize its full potential; it must not be used for the purposes of war, economic competition, or gaining dominance over others.

In other words: artificial intelligence must serve natural intelligence, not the other way around.

New comment by aledevv in "Control the Ideas, Not the Code"

aledevv — Mon, 13 Jul 2026 14:17:30 +0000

>if you control the ideas of your software, looking at the code itself is suboptimal and often pointless.

This requires developers to have absolute and unconditional Trust in the LLM. It's not easy to trust it completely to the point of completely ignoring the implementation details of the code.

In one of Salvatore's discussions, he mentioned that he hasn't even opened a single file of DS4. This is a courageous choice.

But the real question is: if the younger generation stops writing code, how are they supposed to develop that "forma mentis" (mindset) that allows them to reason about design and architecture? It's only by *writing* the code that you gradually internalize development and design patterns, specifically by clashing with the "brutality" of bugs and solving implementation problems.

P.S. I read Wohpe. It's fascinating how back in 2022 (I think?) Salvatore already wrote down many insights that have actually come true (including, for instance, the ban on "strong artificial intelligence"...). So I suppose that the future will touch the very development of humanity (like the Genesi project :) )

New comment by aledevv in "Damaged Earth Catalog"

aledevv — Fri, 10 Jul 2026 10:40:37 +0000

Loving the homage to the Whole Earth Catalog. The pivot from "infinite growth and optimization" to "computing within limits" and permacomputing is becoming less of a fringe philosophy and more of a practical necessity.

As hardware recycling and e-waste become bigger challenges, projects like the Damaged Earth Catalog remind us that modern software bloat is a choice, not an inevitability. We need more focus on resilient, low-power, and maintainable tech stacks.

AI Makes the Cybersecurity Game Faster, Not New

aledevv — Fri, 26 Jun 2026 11:01:17 +0000

Article URL: https://www.rstreet.org/commentary/ai-makes-the-cybersecurity-game-faster-not-new/

Comments URL: https://news.ycombinator.com/item?id=48685149

Points: 2

# Comments: 0

SpaceX will officially acquire Cursor for $60B

aledevv — Thu, 18 Jun 2026 09:07:13 +0000

Article URL: https://fortune.com/2026/06/17/spacex-acquire-cursor-60-billion/

Comments URL: https://news.ycombinator.com/item?id=48582790

Points: 2

# Comments: 1

AI Cyber Tools Move into a New Phase as Governments Tighten Control

aledevv — Wed, 17 Jun 2026 10:04:39 +0000

Article URL: https://freedomforallamericans.org/ai-cyber-tools-government-control/

Comments URL: https://news.ycombinator.com/item?id=48568113

Points: 1

# Comments: 0

New comment by aledevv in "UK Brings in Full Social Media Ban for Under-16s"

aledevv — Mon, 15 Jun 2026 09:14:58 +0000

> “Children will be given back their childhoods,”

As a parent, I completely agree. We need to protect children from the dangers of the completely uncontrolled "jungle" of social media. But above all, we need to give children back the right to experience a true, real childhood, made up of true friends, fresh air, friendships, and real relationships!

AI Study Tools: A Comparison of Flashcard and Spaced Repetition Apps

aledevv — Mon, 15 Jun 2026 08:52:43 +0000

Article URL: https://longtermemory.com/b/ai-study-tools-comparison-2026/

Comments URL: https://news.ycombinator.com/item?id=48538466

Points: 2

# Comments: 1

New comment by aledevv in "Learn SQL Once, Use It for 30 Years"

aledevv — Thu, 04 Jun 2026 08:13:39 +0000

> If you are a junior developer, “learn SQL properly” is the most valuable 40 hours you can spend. Not a tutorial. Not an ORM. Actual SQL: joins, subqueries, window functions, query plans. That investment pays you back at every job, in every stack, for decades

This is the power of low-level reasoning.

Today, even for a junior developers, even if they have AI that solves syntax problems, SQL teaches you to reason and approach problems logically. Without any wrapper masking low-level logic.

It's something like the letters of the alphabet that form concepts: why should they change?

Is grep all you need? Lexical VS Sematic Search for Agents

aledevv — Wed, 27 May 2026 08:20:01 +0000

Article URL: https://www.llamaindex.ai/blog/is-grep-all-you-need-lexical-vs-sematic-search-for-agents

Comments URL: https://news.ycombinator.com/item?id=48291273

Points: 1

# Comments: 0

Google search AI mode, the biggest update

aledevv — Thu, 21 May 2026 08:32:55 +0000

Article URL: https://www.usatoday.com/story/tech/2026/05/20/google-search-ai-mode-biggest-update/90180507007/

Comments URL: https://news.ycombinator.com/item?id=48219539

Points: 2

# Comments: 0

New comment by aledevv in "It is time to give up the dualism introduced by the debate on consciousness"

aledevv — Mon, 18 May 2026 08:45:28 +0000

> ..idea anticipated centuries ago by the philosopher Baruch Spinoza: that our Soul could be a phenomenon of the same basic nature as any other phenomenon in nature.

Even the current Artificial Intelligence revolution is showing us that:

what was thought to be purely immaterial and intangible, that is, human abstract Reasoning and Thoughts, are actually tangible, physical, and even machine-reproducible.