Hacker News: linuxrebe1

New comment by linuxrebe1 in "Corporate Linux"

linuxrebe1 — Thu, 22 Oct 2026 00:23:23 +0000

At the risk of having everybody go full on flame war. I'm going to take a bit of an opposite position. Code written with AI assistance does not require AI to change that code. This article seems to be concentrating on who to blame, for an error in code, rather than concentrating on how in the heck we're going to fix those errors. Saying that if the code was written by/or with the help of, AI, you're now going to have to have corporate sponsorship to fix any subsequent error. Is like saying we can't fix our product anymore because Fred left the company and Fred wrote the original code. Since the mid-90s, much of the development in Linux was done by people with corporate sponsorship. Sometimes third parties, quite often they worked for a distribution. That was a corporation.

New comment by linuxrebe1 in "Jev in 25 Lines of Python"

linuxrebe1 — Wed, 23 Sep 2026 18:13:55 +0000

Mr Smith agrees.

New comment by linuxrebe1 in "Claude Opus 5.5 Intelligence, Performance and Price Analysis (Max)"

linuxrebe1 — Tue, 22 Sep 2026 19:45:46 +0000

Fingers are crossed on this one. I had gone back to using opus 4.8 instead of using opus 5. Simply because 4.8 is much better at remembering what it's doing and following instructions than 5. 5 often had a tendency to get halfway through solving a problem and then I would have to stop it in the middle, because it had lost its way and was going off on a tangent rather than dealing with the problem. In that respect, 4.8 was a lot more stable.

New comment by linuxrebe1 in "Claude Opus 5.5 Intelligence, Performance and Price Analysis (Max)"

linuxrebe1 — Tue, 22 Sep 2026 19:43:21 +0000

Fingers crossed on this one. I had gone back to 4.8, because 5 was not very good at following instructions or remembering instructions. I found myself repeating quite often what I wanted and what I was trying to do. Opus 5 was more like haiku than it was 4.8 in that respect.

New comment by linuxrebe1 in "There's No Limit to How Bad Code Can Get"

linuxrebe1 — Sat, 05 Sep 2026 17:34:49 +0000

Oh and by the way, I will also submit that there is a form of bankruptcy for technical debt.

The company folds, or the software is no longer maintained or in use.

When was the last time you used word Perfect? Or MS-DOS?

New comment by linuxrebe1 in "There's No Limit to How Bad Code Can Get"

linuxrebe1 — Sat, 05 Sep 2026 17:32:47 +0000

As I read this article, as a non-coder (for a living) I noticed that what is being assumed is that the code produces a desired result. To that I will agree. You can really produce some bad code that has a positive outcome.

But as a counter proposal, I will submit that code can get so bad, that the product no longer produces a desirable result, no longer produces it in a manner that people want, or doesn't produce it at all.

Code that produces no desirable result or no result at all. Is as bad as it's going to get. It's a worthless pile of ASCII characters.

New comment by linuxrebe1 in "Ask HN: What are you working on? (August 2026)"

linuxrebe1 — Mon, 10 Aug 2026 03:14:23 +0000

I too got laid off at the end of April. So what I've been working on since then has been AI. But of course, being the contrarian that I am, I'm trying to make small language model AI usable. The end goal is to complete all the pieces I need to create an AI empowered tool that you can point at an authorized Network, and it figures out on its own. What needs to be monitored. Learns what normal looks like on your network. Build your dashboards. Working both as systems monitoring and network monitoring. So right now my GitHub is full of both things that I need, for personal use, in this goal. Also with things that I need because they will become tools for the final product. https://github.com/linuxrebel. You'll get to see my contorted mind at work

New comment by linuxrebe1 in "A Memory Design for Local SLM"

linuxrebe1 — Mon, 10 Aug 2026 02:14:35 +0000

For those of you who remmber the days of monolithic monster programs,you also remember the process of throwing more hardware at the problem. Then someone came along and asked "What if we broke it into chunks and then only load what we are using, when we are using it?

There was a time when the entire OS and the program you were running where both loaded into RAM and you ran from there. Limiting capabilities because hey 1MB of RAM was expensive.

We are reaching a similar point with LLMs. As useful and wonderful as they may be. The idea that you can just through a larger context window at it and it will solve your problem is proving false.It's being proven that the more you have the LLM actively remember, the dumber it can get.

This White Paper marks my research into this issue and what I've found out about how to maximize what an SLM can remember, preserving data integrity, performance,and keeping your data local rather than feeding it to the all consuming.

Feel free to give me feedback and thanks for reading.

A Memory Design for Local SLM

linuxrebe1 — Mon, 10 Aug 2026 02:14:35 +0000

Article URL: https://linuxrebel.github.io/rastro-real/

Comments URL: https://news.ycombinator.com/item?id=49238516

Points: 1

# Comments: 1

New comment by linuxrebe1 in "Turning a pile of documents into a searchable useable knowledge base"

linuxrebe1 — Thu, 09 Jul 2026 19:43:24 +0000

I just had a wild thought. Combine Hister with my RepoSearch app. Point it at a companies Internal github/gitlab and have a searchable knowledge base of your git repos.

New comment by linuxrebe1 in "Turning a pile of documents into a searchable useable knowledge base"

linuxrebe1 — Thu, 09 Jul 2026 19:34:42 +0000

hmmmm :)

New comment by linuxrebe1 in "Turning a pile of documents into a searchable useable knowledge base"

linuxrebe1 — Thu, 09 Jul 2026 19:34:10 +0000

I've run it on a VM with 4G ram and no GPU. It runs, But I really recommend 8G ram at least. If you have a GPU (like I do) with 4G vRAM that is ideal. Will get this in the readme. Thanks for the suggestion. I really tried to build this to minimal spec.

New comment by linuxrebe1 in "Turning a pile of documents into a searchable useable knowledge base"

linuxrebe1 — Thu, 09 Jul 2026 19:22:20 +0000

I fixed this in version 0.9.1 (just released) thanks for the bug (seriously)

New comment by linuxrebe1 in "Turning a pile of documents into a searchable useable knowledge base"

linuxrebe1 — Thu, 09 Jul 2026 19:21:26 +0000

v0.9.1 is in the repo and packages have been built. It now does all of the ODT formats.

New comment by linuxrebe1 in "Turning a pile of documents into a searchable useable knowledge base"

linuxrebe1 — Thu, 09 Jul 2026 19:18:55 +0000

By restricted for personal use I mean it's not networked. It's running on your system only. It's not a networked commercial product able to do SSO etc. It's not an enterprise level product.

New comment by linuxrebe1 in "Turning a pile of documents into a searchable useable knowledge base"

linuxrebe1 — Thu, 09 Jul 2026 19:17:11 +0000

I went with the python libraries (pydoc and pyxls for example), because it's portable and doesn't require a big download to a users system if they don't already have it installed.

New comment by linuxrebe1 in "Turning a pile of documents into a searchable useable knowledge base"

linuxrebe1 — Thu, 09 Jul 2026 16:53:37 +0000

Will have version 0.9.1 out later today to support ODF formats.

New comment by linuxrebe1 in "Turning a pile of documents into a searchable useable knowledge base"

linuxrebe1 — Thu, 09 Jul 2026 16:52:54 +0000

Consider it yes, However having experience in this ... not really. For now there is a file called Decisions.md in the repo that is my "notes to self" if you will about where and what I need to do.

New comment by linuxrebe1 in "Turning a pile of documents into a searchable useable knowledge base"

linuxrebe1 — Thu, 09 Jul 2026 16:50:23 +0000

I use rclone to "mount" them locally. Then it becomes searchable.

New comment by linuxrebe1 in "Turning a pile of documents into a searchable useable knowledge base"

linuxrebe1 — Thu, 09 Jul 2026 16:49:37 +0000

I was building for mac on a VM install of OSX. Will take this as a bug, Thanks.