Hacker News: malka1986

New comment by malka1986 in "EU Age Control: The trojan horse for digital IDs"

malka1986 — Sun, 26 Apr 2026 14:57:20 +0000

they have the lowest approval ratings and legitimization in over half a century, because they're making everything shittier and shittier to the benefit of their corporate overlords.

New comment by malka1986 in "Do you want the US to "win" AI?"

malka1986 — Thu, 23 Apr 2026 11:14:50 +0000

I'm from the EU.

I'd rather China wins this. By a landslide.

I cant wait for the EU finally turns its back on the US and start integrating seriously with China.

New comment by malka1986 in "Obsession with growth is destroying nature, 150 countries warn"

malka1986 — Mon, 16 Mar 2026 13:47:38 +0000

too late anyway.

good luck to all of you.

New comment by malka1986 in "US tech firms pledge at White House to bear costs of energy for datacenters"

malka1986 — Thu, 05 Mar 2026 13:59:34 +0000

The famous communists of hacker news. sigh.

If you are in the US, and are not fascist, I urge you to leave. You are in an equivalent of 1933 germany. It is gonna be dangerous to not bend for the great leader.

New comment by malka1986 in "The L in "LLM" Stands for Lying"

malka1986 — Thu, 05 Mar 2026 08:36:19 +0000

Hello, I am a single dev using an agent (Claude Code) on a solo project.

I have accepted that reading 100% of the generated code is not possible.

I am attempting to find methods to allow for clean code to be generated none the less.

I am using extremely strict DDD architecture. Yes it is totally overkill for a one man project.

Now i only have to be intimate with 2 parts of the code:

* the public facade of the modules, which also happens to be the place where authorization is checked.

* the orchestrators, where multiple modules are tied together.

If the inners of the module are a little sloppy (code duplication and al), it is not really an issue, as these do not have an effect at a distance with the rest of the code.

I have to be on the lookout though. It happens that the agent tries to break the boundaries between the modules, cheating its way with stuff like direct SQL queries.

New comment by malka1986 in "Elevated Errors in Claude.ai"

malka1986 — Tue, 03 Mar 2026 10:57:37 +0000

Unless you are doing stuff that does not need to be maintened, there is still a need for a skilled human to maintain proper software architecture.

It is the managers who are doomed. The future is small team of dev answering directly to the cto.

New comment by malka1986 in "/e/OS is a complete, fully “deGoogled” mobile ecosystem"

malka1986 — Mon, 02 Mar 2026 14:16:23 +0000

I have exactly 0 choice of banks app that would run on a mobile OS that is neither android or google.

At the end of the day, I need a bank account, and access to it, would it only be for buying food, or paying my mortgage.

New comment by malka1986 in "/e/OS is a complete, fully “deGoogled” mobile ecosystem"

malka1986 — Mon, 02 Mar 2026 13:58:47 +0000

I need my bank app to run on it.

New comment by malka1986 in "Euro firms must ditch Uncle Sam's clouds and go EU-native"

malka1986 — Sat, 31 Jan 2026 12:59:19 +0000

Yeah and we could run kimi. Th issue is energy, we should keep building nuclear reactor and renewable to power it.

New comment by malka1986 in "OpenAI’s unit economics"

malka1986 — Thu, 29 Jan 2026 15:19:02 +0000

If the clone is 1/10th of the price, and of equivalent quality, why would I use the original ? I would be undercut by my concurrents if i did that, it would be a very bad business decision.

New comment by malka1986 in "OpenAI’s unit economics"

malka1986 — Thu, 29 Jan 2026 10:59:56 +0000

> Isn't there pretty good indications that the chinese llms have been trained on top of the expensive models?

So what ?

New comment by malka1986 in "Claude is good at assembling blocks, but still falls apart at creating them"

malka1986 — Fri, 16 Jan 2026 12:23:43 +0000

I am making an app in Elixir.

100% of code is made by Claude.

It is damn good at making "blocks".

However, Elixir seems to be a langage that works very well for LLM, cf. https://elixirforum.com/t/llm-coding-benchmark-by-language/7...

New comment by malka1986 in "First impressions of Claude Cowork"

malka1986 — Fri, 16 Jan 2026 09:05:18 +0000

you have to be crazy to run claude in YOLO mode outside of a constrained environment such as a docker container

New comment by malka1986 in "Rainbow Six Siege hacked as players get billions of credits and random bans"

malka1986 — Sun, 28 Dec 2025 15:27:08 +0000

Hopefully, AAA games era is coming to an end.

New comment by malka1986 in "Wall Street races to protect itself from AI bubble"

malka1986 — Fri, 05 Dec 2025 19:09:25 +0000

China made the us fall in kinda the same trap that the us madeade ussr fall into with the moon race.

New comment by malka1986 in "SmartTube Compromised"

malka1986 — Mon, 01 Dec 2025 19:33:37 +0000

It is yes. Your ability to create new meaning for words is awesome.

New comment by malka1986 in "SmartTube Compromised"

malka1986 — Mon, 01 Dec 2025 19:08:04 +0000

The reason its not stealing is because stealing means to remove someone of the ownership of something they own.

You are able to make your own définition though. The clear mark of a very intelligent mind.

New comment by malka1986 in "SmartTube Compromised"

malka1986 — Mon, 01 Dec 2025 18:40:05 +0000

Blocking ads is the same as stealing.

You are very intelligent.

New comment by malka1986 in "SmartTube Compromised"

malka1986 — Mon, 01 Dec 2025 09:57:11 +0000

Google is free to block me / my IP / ban my account.

New comment by malka1986 in "SmartTube Compromised"

malka1986 — Mon, 01 Dec 2025 09:27:29 +0000

I hate google, and I refuse to give them any money.