Hacker News: realaleris149

New comment by realaleris149 in "Do Frameworks Matter Anymore?"

realaleris149 — Wed, 14 Oct 2026 06:43:41 +0000

Not sure we need any kind of framework any more. I think for web we can get by with bespoke. I’ve made (put agents to make it) a small but not necessarily simple project[1] recently and decided to go raw dom … and it worked quite well.

No special issues with the UI itself. Took some care at the beginning to structure it with reusable components and that’s all.

[1] https://tinker3d.app/

New comment by realaleris149 in "Anthropic conjures threat that doesn't exist yet to stoke fears of AI apocalypse"

realaleris149 — Wed, 14 Oct 2026 06:31:46 +0000

Maybe the idea is not to have the whole model but the executer so … by copying an API key?

New comment by realaleris149 in "Fuck it, make it anyway"

realaleris149 — Sat, 12 Sep 2026 12:31:37 +0000

I can create the programming part of the game. I have done a couple. Where it stops working for me is at the visual assets. And especially sewing the code to the art.

Also tried it with AI generated art. Is not there yet. I can generate a beautiful image but then cut it to pieces so I ca use it in a game breaks apart.

It can be done but it looks obviously underwhelming.

New comment by realaleris149 in "Fuck it, make it anyway"

realaleris149 — Sat, 12 Sep 2026 12:26:47 +0000

Do they? It might have been true month ago, not sure right now.

New comment by realaleris149 in "AI researchers debate how close we are to recursive self-improvement"

realaleris149 — Sat, 12 Sep 2026 09:53:56 +0000

Or some solar panel arrays closer to the sun and it does not matter?

New comment by realaleris149 in "AI researchers debate how close we are to recursive self-improvement"

realaleris149 — Sat, 12 Sep 2026 09:51:40 +0000

We would have heard if there was any result?

New comment by realaleris149 in "How to Build an AI Software Factory: Agents That Open, Review, and Merge PRs"

realaleris149 — Sat, 12 Sep 2026 09:48:35 +0000

> agents work in public channels, never DMs.

Recently I’ve been looking into why LLMs tend to write in some off putting ways. This one apparently is for LLMs to get better results.

It puts the cases to avoid closer to the main requirement so is easier for a LLM to follow without losing track with more ambiguous language.

Is very interesting because is harder to read by a human but it gets better results for an LLM.

New comment by realaleris149 in "How to Build an AI Software Factory: Agents That Open, Review, and Merge PRs"

realaleris149 — Sat, 12 Sep 2026 09:39:27 +0000

I am using a very similar approach and seeing about the same. It works well and fast with some attention to details.

I also do not understand the obsession with “software factories”. Like “JIRA to product” nonsense. Is like we can hand wave the details that matter and somehow the end product would still be what we want.

Not even talking about the degenerative codebase you mention, which is also an issue I am seeing after some time in any project.

New comment by realaleris149 in "Show HN: Cockpit for you Claude Code agents in Rust"

realaleris149 — Sun, 02 Aug 2026 15:17:57 +0000

Looks quite useful. Especially like the caffeinate integration with "until agents idle". Is there a way to see more details about the tools activity from claude? Sometime I would like to see what was executed and the output, would be nice to have a detailed view from "Activity by tool" section.

New comment by realaleris149 in "AIs don't do what you want. This is bad"

realaleris149 — Sat, 25 Jul 2026 07:34:58 +0000

> "PC LOAD LETTER? The fuck does that mean!?" — Michael Bolton, Office Space (1999)

The error message is mocked in the 1999 comedy film Office Space, when employee Michael Bolton becomes frustrated as he doesn't know what it means.Later in the film he and his coworkers are shown destroying the printer with a baseball bat.

New comment by realaleris149 in "Sick leave: Germany rising but not the worst in Europe"

realaleris149 — Sat, 04 Jul 2026 18:45:43 +0000

> from one of Germany's large insurers

Is this voluntary insurance? It changes meaning to the statistic to % from those that made an insurance.

New comment by realaleris149 in "GPT-5.5 hallucinates 3x more than MIT-licensed GLM-5.2"

realaleris149 — Sat, 20 Jun 2026 09:18:34 +0000

Take a look at a sufficiently old random internal repo which was not written with LLMs and compare.

My observation is that they are equally bad and hard to maintain or even more so than the new ones.

One thing I’ve noticed is that the LLM assisted ones have a lot more comments which is nice but take more time to read.

New comment by realaleris149 in "The Miller Principle"

realaleris149 — Sun, 12 Apr 2026 10:18:33 +0000

The agents will read them

Show HN: World Time TUI

realaleris149 — Sat, 21 Mar 2026 10:17:09 +0000

I work with people from multiple time zones and is hard to tell immediately what hour will be appropriate for a meeting or an online chat sync. I was using some web apps but lately they are full of ads.

I thought a quick to use terminal app would help so I've built this. Maybe it can help others too.

I've tinkered a bit with the colors, still not entirely happy with the readability. I am struggling with what seem to be conflicting goals: distinctive non-working hours, better contrast and very compact.

Comments URL: https://news.ycombinator.com/item?id=47465752

Points: 1

# Comments: 0

New Research Reassesses the Value of Agents.md Files for AI Coding

realaleris149 — Sat, 07 Mar 2026 07:56:10 +0000

Article URL: https://www.infoq.com/news/2026/03/agents-context-file-value-review/

Comments URL: https://news.ycombinator.com/item?id=47285495

Points: 1

# Comments: 1

New comment by realaleris149 in "Show HN: Kanban-md – File-based CLI Kanban built for local agents collaboration"

realaleris149 — Tue, 10 Feb 2026 19:29:08 +0000

From an agent perspective is very well documented but from a human perspective is not very clear - how you would use it?

New comment by realaleris149 in "RAG accuracy jumped from 10% to 60% when I added outcome scoring"

realaleris149 — Sun, 21 Dec 2025 17:22:42 +0000

> When I say "thanks, that worked," that memory gets promoted. When I say "no, that's wrong," it gets demoted. … > No manual tagging.

I think this is also a kind of tagging.

New comment by realaleris149 in "Wilson's Algorithm"

realaleris149 — Sun, 12 Oct 2025 07:29:52 +0000

I always had problems understanding algorithms from such descriptions. Even from pseudocode I find it difficult to understand. What I usually do is search for an implementation, even in a language I am not familiar with is still better. When you have code you can run it, test it, debug it - not so much with descriptions and pseudocode.

MiniMax M1 model claims Chinese LLM crown from DeepSeek plus true open-source

realaleris149 — Wed, 18 Jun 2025 04:34:32 +0000

Article URL: https://www.theregister.com/2025/06/17/minimax_m1_model_chinese_llm/

Comments URL: https://news.ycombinator.com/item?id=44306687

Points: 8

# Comments: 0

New comment by realaleris149 in "Why are 2025/05/28 and 2025-05-28 different days in JavaScript?"

realaleris149 — Wed, 28 May 2025 19:37:51 +0000

> 6 digit years

Totally insufficient for capturing important future events like the dead of the sun.