Hacker News: monatron

New comment by monatron in "OpenAI is well positioned to fast-follow Jev"

monatron — Tue, 22 Sep 2026 14:59:32 +0000

I would assume that they would fold this type of classification into their responses API next to existing ancillary tooling that they already ship. I think OpenAI positions themselves as being wholly focused on AGI - but I think their business model leans towards lock-in via superior tooling (Codex, ChatGPT, etc.). This feels like an easy win for them without muddying the larger vision.

New comment by monatron in "Navier-Stokes Announcement"

monatron — Sat, 12 Sep 2026 10:52:18 +0000

This was the first thing I noticed as well. It was refreshing to read.

New comment by monatron in "Apple caught off guard by AI demand for Mac Mini and Mac Studio"

monatron — Mon, 31 Aug 2026 13:50:36 +0000

I think your last point is exactly why I'm so interested in local models. The current landscape doesn't feel sustainable. The last few months we've seen the big providers (OpenAI, Anthropic) start to play with usage limits, resets, banked resets, pulling models, etc. I think local models are close to the point where, with a sufficiently well-architected harness, you can get results that are on par with the experience you'd have with cloud inference. It is nice to know that I have hardware under my desk that I control with open weight models that I can interact with on my terms.

New comment by monatron in "Issue: Claude Code is unusable for complex engineering tasks with Feb updates"

monatron — Mon, 06 Apr 2026 19:36:14 +0000

To be fair, I can think of reasons why you would want to be able to set them in various ways.

- settings.json - set for machine, project

- env var - set for an environment/shell/sandbox

- slash command - set for a session

- magical keyword - set for a turn

New comment by monatron in "Vibe a Guitar Pedal"

monatron — Fri, 23 Jan 2026 01:13:52 +0000

Very cool! Would love to know more about the audio processing backend that drives this type of thing

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

monatron — Sun, 11 Jan 2026 18:36:05 +0000

I'm on a deep dive fine-tuning how I organize and manage my personal knowledge base - focused on entity extraction and strategic information retrieval and based on the AgREE paper from Apple[0] and persisting it in Memgraph.

I've got a nice ingest, extract, enrich process going for the graph - I'm currently working on a fork of claude-mem[1] that uses the graph as a contextual backend for agentic coding workflows.

0. https://arxiv.org/abs/2508.04118 1. https://github.com/thedotmack/claude-mem/

New comment by monatron in "AI is forcing us to write good code"

monatron — Mon, 29 Dec 2025 23:23:24 +0000

If you're like me you're doing it to establish a greater level of trust in generated code. It feels easier to draw out the hard guard-rails and have something fill out the middle -- giving both you, and the models, a reference point or contract as to what's "correct"

New comment by monatron in "GPT-5.2"

monatron — Fri, 12 Dec 2025 10:29:50 +0000

Nice tool - I appreciate you sharing the work!

Show HN: GimmeGimme – Finding gifts for hard-to-shop-for people

monatron — Thu, 27 Nov 2025 18:55:58 +0000

Hi y'all, it's that time of year -- you're going to visit the in-laws and you have no idea what to get Uncle Bobby this holiday but you don't want to show up with something boring or generic. You want to find a gift that fits.

I scoured through hundreds of 2025 Holiday Gift Guides, and built a little workflow that combines some scraping, prompt chains, and embeddings that matches the description of a person with a set of gifts that might be a good fit for them. The lists persist, and you can remove items from them to get new suggestions and iterate on the lists until you find some options that make sense for you.

This was built mostly for fun, but full disclosure, there's Amazon Affiliate tags for the items presented.

I'm open to feedback. Hope this helps you find something unique for that person that's hard shop for.

Happy Thanksgiving, Tyler

Comments URL: https://news.ycombinator.com/item?id=46072187

Points: 1

# Comments: 0

New comment by monatron in "Claude Opus 4.1"

monatron — Tue, 05 Aug 2025 17:15:21 +0000

This is a great use case for sub-agents IMO. By default, sub-agents use sonnet. You can have opus orchestrate the various agents and get (close to) the best of both worlds.

New comment by monatron in "Show HN: I've been building an ERP for manufacturing for the last 3 years"

monatron — Tue, 05 Aug 2025 12:15:57 +0000

Did you folks roll this yourself? I like the learning platform and was trying to figure out what you've might have used to build it.

New comment by monatron in "Show HN: Apple Health MCP Server"

monatron — Fri, 25 Jul 2025 13:00:42 +0000

Very cool indeed. I started building something similar - relying on Auto Export [https://apps.apple.com/us/app/health-auto-export-json-csv/id...] to export my health data to an endpoint which stores it in a sqlite database. I never got as far as building an MCP server around the data but that's certainly the direction I was heading. The initial idea was to use my health data to provide context to a health/fitness agent that would recommend workouts, check-in on things, etc.

New comment by monatron in "I watched Gemini CLI hallucinate and delete my files"

monatron — Tue, 22 Jul 2025 20:09:26 +0000

Claude will do this. I've seen it create "migration scripts" to make wholesale file changes -- botch them -- and have no recourse. It's obviously _not great_ when this happens. You can mitigate this by running these agents in sandbox environments and/or frequently checkpointing your code - ideally in a SCM like git.

New comment by monatron in "N8n vs. node-red"

monatron — Sat, 19 Jul 2025 00:04:55 +0000

There are a lot of nodes that are pre-built to interact with cloud APIs, but you effectively have an HTTP client available that can reach out to any endpoint. In my case, yes, I make use of cloud APIs and realize the trade-offs wrt privacy. You can hit any internal services you like assuming they're reachable from your n8n server

New comment by monatron in "N8n vs. node-red, which to use for AI workloads"

monatron — Thu, 17 Jul 2025 12:51:09 +0000

I self-host n8n and get a ton of mileage out of it. Doesn't cost me a dime.

New comment by monatron in "If nothing is curated, how do we find things"

monatron — Tue, 20 May 2025 15:36:18 +0000

I'm referring to LLMs

New comment by monatron in "If nothing is curated, how do we find things"

monatron — Sat, 17 May 2025 18:07:56 +0000

We have tools today that are uniquely good at wading through disparate sources and aggregating things into a format that we can easily digest. The worry of course - is that these tools are generally on offer from huge tech giants (google, openai, etc). The good news is, we have open-source versions of these tools that perform almost as well as the closed-source versions for these types of categorization and aggregation.

I would agree that information is now more scattered (like bread for ducks as the author notes) than ever before -- but we now have the unprecedented ability to wrangle it ourselves.

New comment by monatron in "Show HN: Sim Studio – Open-Source Agent Workflow GUI"

monatron — Mon, 28 Apr 2025 18:02:25 +0000

Hi y'all. Love the idea and congratulations on your launch. I've used [n8n](https://github.com/n8n-io/n8n) for similar use cases in the past. Any differences in Sim Studio that you'd like to call out?

New comment by monatron in "Copilot vs. Cursor vs. Cody vs. Supermaven vs. Aider"

monatron — Fri, 25 Oct 2024 13:28:18 +0000

I'm surprised continue.dev isn't getting a mention here. I've tried copilot, cody, and cursor, and ultimately came back to continue.dev. I can use my own models, api key, etc. The same VSCode setup I'm used to, custom context providers, doc indexing, etc. It's proven to be extremely useful for me - though I use it less for autocomplete, and more for interactive back-and-forth sessions to arrive at a block of code.

New comment by monatron in "Working remotely can more than halve an office employee’s carbon footprint"

monatron — Fri, 22 Sep 2023 17:17:50 +0000

I used to work for a Fortune 500 company and in my case it was obvious that businesses in and around our campus suffered significantly with more people not coming to the office. My guess is the company had tax incentives in place with the city/state on the condition that their being there was a boost for the local economy. People not coming to work and spending money jeopardized those incentives.