Hacker News: Scotrix

New comment by Scotrix in "Chuck Norris has died"

Scotrix — Fri, 20 Mar 2026 19:17:17 +0000

Chuck Norris doesn’t die.

New comment by Scotrix in "Ask HN: Share your personal website"

Scotrix — Thu, 15 Jan 2026 09:50:49 +0000

https://portfolio.gomsilo.com

New comment by Scotrix in "Dedicated GPU Server from Hetzner"

Scotrix — Thu, 11 Dec 2025 07:37:02 +0000

Quite a beast for a very good price…

Dedicated GPU Server from Hetzner

Scotrix — Thu, 11 Dec 2025 07:37:02 +0000

Article URL: https://www.hetzner.com/dedicated-rootserver/matrix-gpu/

Comments URL: https://news.ycombinator.com/item?id=46228677

Points: 5

# Comments: 1

New comment by Scotrix in "Anti-patterns while working with LLMs"

Scotrix — Fri, 28 Nov 2025 20:44:52 +0000

I played a lot with LLMs over the last year and built a multitude of products with it and it’s always just the same bottom line outcome: - be specific - keep it small - be precise when adding context - don’t expect magic and shift deterministic requirements to deterministic code execution layers

All this is awfully painful to manage with current frameworks and SDKs, somehow a weird mix of over-engineered stuff while missing the actual point of making things traceable and easy changeable once it gets complex (my unpopular personal opinion, sorry). So I have built something out of my own need and started to offer it (quite successfully so far)to family & friends to get a handle on it: Have a look: https://llm-flow-designer.com

New comment by Scotrix in "Agent design is still hard"

Scotrix — Sat, 22 Nov 2025 20:21:45 +0000

While working on a new startup I had exactly the same challenges and issues. As soon as it gets complex, data gets bigger, amount of tools increases it becomes tremendously difficult to control agents, network of agents or anything LLM related. Add then specific domains like legal or finance where most of the time there is just 0 or 1 and nothing in between (metaphorical speaking) it becomes a nightmare in code and side effects.

So I started to actually build something to solve most of my own problems reliably and pushing deterministic outputs with help of LLMs (e.g. imagine finding the right columns/sheets in massive spreadsheets to create tool execution flows and fine tuning finding a range of data sources). My idea and solution which helped not only me but also quite a few business folks so far to fix and test agents is visualizing flows, connect and extract data visually, test and deploy changes in real time while keeping it very close to static types and predictable output (other than e.g. llama flow).

Would love to hear your thoughts about my approach: https://llm-flow-designer.com

New comment by Scotrix in "Ask HN: How to stop an AWS bot sending 2B requests/month?"

Scotrix — Fri, 17 Oct 2025 06:34:31 +0000

Just find a Hoster with low traffic egress cost, reverse proxy normal traffic to Cloudflare and reply with 2GB files for the bot, they annoy you/cost you money, make them pay.

New comment by Scotrix in "Modern Linux tools"

Scotrix — Mon, 13 Oct 2025 11:33:50 +0000

would be good to have an indicator if it’s available with your distro by default or what package you’ll need to install it since all tools are only as useful as available they are…

New comment by Scotrix in ""Vibe code hell" has replaced "tutorial hell" in coding education"

Scotrix — Fri, 10 Oct 2025 17:39:16 +0000

+1 I dropped school relatively early (I was extremely bored and the way of education was certainly somewhere close from the Stone Age times). I did an apprenticeship as software engineer with some (extremely useless) school component. Most of the time in the late 90ties was trial and error, for me, the master and the master of masters. Playing around with Linux and make it ISDN routers with servers for websites built in HTML, Perl, PHP. This was devops (before it got hyped) and real engineering by figuring stuff out with almost no documentation, a lot of crazy creativity and push the boundaries of what’s possible. And it reminds me just a little like today’s world with AI and vibe coding just on a complete different level and with significant more pressure…fun times :-).

New comment by Scotrix in "Ask HN: LLM Prompt Engineering"

Scotrix — Fri, 19 Sep 2025 10:46:09 +0000

cool, i'll have a look. thanks for sharing.

New comment by Scotrix in "Ask HN: LLM Prompt Engineering"

Scotrix — Thu, 18 Sep 2025 15:48:01 +0000

I input text and preferably I output JSON but doesn’t matter much as long as it’s somewhat structured.

Ultimately I’d like to extract information like date ranges, specific indications of tool usages (e.g. I have a bunch of data apis with their own individual data and semantic meaning which need to be picked and then a combination of tools to transform the data)

New comment by Scotrix in "Ask HN: Degraded Mac performance on macOS 26 Tahoe?"

Scotrix — Thu, 18 Sep 2025 14:12:58 +0000

The first few seconds/minutes I felt the same but it was fine quite fast. I think the typical spotlight reindexing was the culprit.

Ask HN: LLM Prompt Engineering

Scotrix — Thu, 18 Sep 2025 14:11:27 +0000

I’m working on a project where I need to extract user intents and move them to deterministic tool/function/api executions + afterwards refining/transforming the results by another set of tools. Since gathering the right intent and parameters (there are a lot of subtle differences in potential prompts) is quite challenging I’m using a long consecutive executed list of prompts to fine tune to gather exactly the right pieces of information needed to have somewhat reliable tool executions. I tried this with a bunch of agent frameworks (including langchain/langgraph) but it gets very messy very quickly and this messiness is creating a lot of side effects easily.

So I wonder if there is a tool, approach, anything to keep better control of chains of LLM executions which don’t end up in a messy configuration and/or code execution implementation? Maybe even something more visual, or am I the only struggling with this?

Comments URL: https://news.ycombinator.com/item?id=45289941

Points: 5

# Comments: 4

New comment by Scotrix in "How I Use Kagi"

Scotrix — Thu, 17 Jul 2025 19:17:35 +0000

I switched as well and I actually use the AI assistant since then primarily. It’s awesome to connect search directly with AI, almost always get what I want immediately.

New comment by Scotrix in "A critical look at MCP"

Scotrix — Sat, 10 May 2025 20:33:39 +0000

yeah, but it doesn’t need to be that way. It can be simple and makes it easier adoptable, why over engineering and reinventing the wheel of at least 2 decades experience and better practices.

New comment by Scotrix in "A critical look at MCP"

Scotrix — Sat, 10 May 2025 20:13:53 +0000

OpenAI takes the backseat and wait until something stable/usable comes out of it which gains traction and takes it over then. Old classic playbook to let others make the mistakes and profit from it…

New comment by Scotrix in "A critical look at MCP"

Scotrix — Sat, 10 May 2025 19:43:13 +0000

Couldn’t agree more, played the whole day today trying to get a HTTP MCP server with Claude running.

Absolutely terrible, no clear spec, absolute useless errors and/or just broken behaviour without telling what’s wrong. Reference implementations and frameworks are not working either, so only reverse engineering + trial & error until it runs, yaaay.

Feels like the early 2000 over and over again, trying to make something work.

New comment by Scotrix in "Undocumented backdoor found in Bluetooth chip used by a billion devices"

Scotrix — Sat, 08 Mar 2025 20:27:08 +0000

wasn’t vo1d something which could potentially deliver in this?

New comment by Scotrix in "Bybit loses $1.5B in hack but can cover loss, CEO confirms"

Scotrix — Sat, 22 Feb 2025 18:24:22 +0000

well, min. required network confirmations could still replace the progress bar. I certainly pressed reload anxiously quite a few times :-)

New comment by Scotrix in "We got hit by an alarmingly well-prepared phish spammer"

Scotrix — Thu, 30 Jan 2025 09:10:07 +0000

No auth smtp server sounds like a very bad idea and the real culprit here. Security by obscurity (VPN in this case) never works.