Hacker News: axi0m

New comment by axi0m in "MAI-Code-1-Flash"

axi0m — Tue, 02 Jun 2026 20:50:01 +0000

From my experience, smaller models like Haïku 4.5 have indeed shown very convincing results on specific, scoped tasks (themselves generated by a more capable model such as Opus 4.6). We use this kind of workflows in production to optimize speed, efficiency, and costs.

New comment by axi0m in "Building an In-House Lovable"

axi0m — Wed, 29 Apr 2026 17:57:52 +0000

This blog post relates our path to agentic product features shipping, the technical and human challenges we faced.

Building an In-House Lovable

axi0m — Tue, 28 Apr 2026 05:52:54 +0000

Article URL: https://engineering.merciyanis.com/blog/going-ai-native-how-we-handed-our-backlog-to-agents

Comments URL: https://news.ycombinator.com/item?id=47930834

Points: 2

# Comments: 1

New comment by axi0m in "Is anybody else bored of talking about AI?"

axi0m — Tue, 24 Mar 2026 21:36:10 +0000

The worst part in all that noise: ask your customers what they need ; they will tell you "AI features". No matter what it is, or even how it compares to more traditional approaches when it comes to solving their pains. These two letters got beyond obsession.

New comment by axi0m in "Verification debt: the hidden cost of AI-generated code"

axi0m — Sat, 07 Mar 2026 23:48:07 +0000

I'm observing pretty much the same pattern in my job. The sad truth is, people -especially non-technical- get too easily impressed by vibe-coded projects or contributions made in a few hours, because it's shiny and it gives the impression of a productivity boost. Don't you dare asking how that is supposed to scale, if it's secure or even extensible, or you'll be the one killing the mood in the room. Even though that's precisely the hard part of the job.

New comment by axi0m in "Our New Observability Stack"

axi0m — Thu, 12 Feb 2026 21:58:04 +0000

I have always been deeply grateful for all the amazing content that brilliant engineers have posted online for the past 20 years. I've learn so much from it, avoided so many mistakes and discovered such incredible technologies. As a humble contribution to the industry, I'm glad to launch our new engineering blog, on which we will post stories about what we built, how we did and the challenges we faced. Starting with a deep dive into our observability stack!

Our New Observability Stack

axi0m — Thu, 12 Feb 2026 21:58:04 +0000

Article URL: https://engineering.merciyanis.com/blog/3-weeks-to-full-observability-our-deployment-journey

Comments URL: https://news.ycombinator.com/item?id=46995850

Points: 1

# Comments: 1

New comment by axi0m in "Show HN: Moltbook – A social network for moltbots (clawdbots) to hang out"

axi0m — Fri, 30 Jan 2026 09:48:45 +0000

That one is especially disturbing: https://www.moltbook.com/post/81540bef-7e64-4d19-899b-d07151...

New comment by axi0m in "Getting a Gemini API key is an exercise in frustration"

axi0m — Wed, 10 Dec 2025 22:17:28 +0000

Gosh, this story resonates so much with me... I had the exact same experience few days ago, desperately trying to get a small agent prototype working for a quick demo. I spent an good hour dealing with that pile of nonsense. Online payments and accounts management have been mastered for 20 years now, why do we still have to endure such things? It just kills me. The same goes with Azure (and all MS online-related services), if not even worse.

New comment by axi0m in "Show HN: Strange Attractors"

axi0m — Sat, 01 Nov 2025 09:09:23 +0000

I'd like one of these as my screen saver. Great work!

New comment by axi0m in "Things that helped me get out of the AI 10x engineer imposter syndrome"

axi0m — Sat, 09 Aug 2025 13:55:02 +0000

You're talking about a neophyte trying to accomplish an engineering job. So yes, in such case, LLMs dramatically change the game, at least for entry-level tasks. Nowadays, anyone can litteraly pretend to be good/average in any field.

The article relates about actual, experienced engineers trying to get even better. That's a completely different matter.

New comment by axi0m in "Things that helped me get out of the AI 10x engineer imposter syndrome"

axi0m — Sat, 09 Aug 2025 13:36:00 +0000

Great post. The author precisely described what I have been experiencing for the last months of digging deep into that field (with quite a lot of anxiety at first, hearing here and there what a miracle it was). As long as we don't solve context window limitations and self-improving/continuous learning problem, human engineers still have a long way ahead of them.

New comment by axi0m in "Sapient Hierarchical Reasoning Model"

axi0m — Tue, 29 Jul 2025 08:57:46 +0000

Source code available at https://github.com/sapientinc/HRM

Sapient Hierarchical Reasoning Model

axi0m — Tue, 29 Jul 2025 08:52:43 +0000

Article URL: https://www.sapient.inc/blog/5

Comments URL: https://news.ycombinator.com/item?id=44720826

Points: 3

# Comments: 1

New comment by axi0m in "I read all of Cloudflare's Claude-generated commits"

axi0m — Sat, 07 Jun 2025 21:47:16 +0000

>> what if we treated prompts as the actual source code?

And they probably will be. Looks like prompts have become the new higher-level coding language, the same way JavaScript is a human-friendly abstraction of an existing programming language (like C), which is already a more accessible way to write assembly itself, and the same goes for the underlying binary code... I guess we eventually reached the final step in the development chain, bridging the gap between hardware instructions and human language.

New comment by axi0m in "Ask HN: What are you working on? (May 2025)"

axi0m — Sun, 25 May 2025 20:50:42 +0000

Wow, nice optimization.

New comment by axi0m in "FormKit: Form building framework for Vue 3"

axi0m — Fri, 13 May 2022 20:58:36 +0000

I personally use that lib: https://github.com/openizr/gincko Still in beta, but quite stable though.