Hacker News: mackross

New comment by mackross in "Go: Support for Generic Methods"

mackross — Wed, 27 May 2026 15:26:13 +0000

What a happy surprise today! The amount of times I’ve had to do weird janky package APIs so the API was still reasonable is more than I can count.

New comment by mackross in "Kindle loyalists scramble as Amazon turns page on old e-readers"

mackross — Sun, 24 May 2026 12:10:39 +0000

moved to kobo (the nice one with colour screen) with calibre web running behind a cloudflare tunnel, getting books direct through smallest publishers/authors. Adds the tiniest bit of friction in book acquisition but reading experience, battery life, everything else shits on my kindle experience (and I’ve owned every one).

New comment by mackross in "Gemini 3.5 Flash"

mackross — Tue, 19 May 2026 19:36:42 +0000

The antigravity teamwork-preview doesn't work for me -- upgraded to ultra, installed antigravity 2, ran teamwork-preview, keeps failing: "You have exhausted your capacity on this model. Your quota will reset after 0s."

New comment by mackross in "What years of production-grade concurrency teaches us about building AI agents"

mackross — Mon, 23 Feb 2026 22:40:41 +0000

Durable objects looks interesting! Thanks for the link

New comment by mackross in "What years of production-grade concurrency teaches us about building AI agents"

mackross — Thu, 19 Feb 2026 12:22:13 +0000

I’m a huge elixir fan, but imho it doesn’t solve durable execution out of the box which is a major problem that often gets swept under the rug by BEAM fanboys. Because ETS and supervision trees don’t play well with deployment via restart, you’ve got to write some level of execution state to relational database or files. You can choose persistent ETS, mnesia, etc, (which have their own tradeoffs and come with some kind of gnarley data-loss scenarios in deep documentation). But, whatever you choose, in my experience you will need to spend a fair amount of time considering how your processes are going to survive restarts. Alternatively, Oban is nice, but it’s a heavy layer that makes control flow more complex to follow. And, yes you can roll your own hot code deploy and run in persistent VMs/bare metal and be a true BEAM native, but it’s not easy out of the box and comes with its own set of foot guns. If I’m missing something, I would love for someone to explain to me how to do things better, as I find this to be a big pain point whenever I pick up elixir. I want to use the beautiful primitives, but I feel I’m always fighting durable execution in the event of a server restart. I wish a temporal.io client or something with similar guarantees was baked into the lang/frameworks.

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

mackross — Mon, 09 Feb 2026 18:30:27 +0000

- A phoenix/ecto inspired batteries included framework for Golang. Uses data-star for real time bindings (can do live view like things but my personal favorite is just real time form validation out of the box). Hot reload with templ, daisy, and tailwind (no npm required). Routes file provides metadata on routes so type safe route helpers are generated for views and handlers.

New comment by mackross in "Lix – universal version control system for binary files"

mackross — Thu, 22 Jan 2026 18:23:26 +0000

Same name as my Phoenix inspired framework for go: https://codeberg.org/lixgo/lix

New comment by mackross in "Mistral 3 family of models released"

mackross — Wed, 03 Dec 2025 12:32:40 +0000

Cool app. I couldn’t see a way to report an error in one of the default expressions.

New comment by mackross in "Google, Nvidia, and OpenAI"

mackross — Mon, 01 Dec 2025 22:48:27 +0000

Guess my edit didn’t work…

New comment by mackross in "Google, Nvidia, and OpenAI"

mackross — Mon, 01 Dec 2025 19:10:58 +0000

An often overlooked extra advantage to Google is their massive existing ad inventory. If LLMs do end up being ad supported and both products are roughly the same, Google wins. The large supply of ads direct from a diverse set of advertisers means they can fill more ad slots with higher quality ads, for a higher price, and at a lower cost. They’re also already staffed with an enormous amount of talent for ad optimization. Just this advantage would translate into higher sustained margins (even assuming similar costs), but given TPU it might be even greater. This plus the gobs of cash they already spin off, and their massive war chest means they can spend an ungodly amount on user acquisition. It’s their search playbook all over again.

New comment by mackross in "Google, Nvidia, and OpenAI"

mackross — Mon, 01 Dec 2025 19:10:10 +0000

An often overlooked extra advantage to Google is their massive existing ad inventory. If LLMs do end up being ad supported and both products are roughly the same, Google wins. The large supply of ads direct from a diverse set of advertisers means they can fill more ad slots with higher quality ads, for a higher price, and at a lower cost. They’re also already staffed with an enormous amount of talent for ad optimization. Just thus advantage would translate into higher sustained margins (even assuming similar costs), but given TPU it might be even greater. This plus the gobs of cash they already spin off, and their massive war chest means they can spend an ungodly amount on user acquisition. It’s their search playbook all over again.

New comment by mackross in "Fnox, a secret manager that pairs well with mise"

mackross — Mon, 27 Oct 2025 17:56:22 +0000

Love the thought put into mise and now fnox. They’re a joy to use.

New comment by mackross in "Reverse engineering iWork"

mackross — Wed, 15 Oct 2025 17:38:52 +0000

Amazing work by author!

New comment by mackross in "Uncertain"

mackross — Thu, 28 Aug 2025 18:28:01 +0000

Always enjoy mattt’s work. Looks like a great library.

Show HN: Instruct LLMs to do what you want in Ruby

mackross — Fri, 20 Dec 2024 12:58:34 +0000

I’ve been working on this gem part-time for a few months now. The API is not yet fully stable so I wouldn’t recommend for anything other than experimenting. Nevertheless, my company is using it in production (as of today :)), so it seemed like a nice time to share.

So why did I write yet another LLM prompting library?

I found the existing Ruby ones either too abstract — hiding the LLM’s capabilities behind unseen prompts, too low-level — leaving my classes hard to follow and littered with boilerplate managing prompts and responses, or they used class level abstractions — forcing me to create classes when I didn’t want to.

After reading an early version of Patterns of Application Development Using AI by Obie Fernandez and using Obie’s library raix, I felt inspired. The book has many great patterns, and raix’s transcript management and tool management were the first I’d used that felt ruby-ish. At the same time libraries in the python community such as guidance, DSPy, LangSmith, and TEXTGRAD had caught my eye. I also liked what the cross-platform BAML was doing too. I didn’t love the code generation and freemium aspects.

So, with motivation high, I set out to build an opinionated library of gems that improves my Ruby (and Rails) LLM developer experience.

The first gem (this one) is instruct. It is the flexible foundation that the other gems will build on. While the API is similar to guidance, it has a different architecture based around attributed strings and middleware which enables some unique features (like async guard rails, content filters, self-healing, auto-continuation, and native multi-modal support).

I’m currently working on a hopefully elegant API that makes requesting and handling streaming structured output easy (taking inspiration from BAML, but with automatic upgrades to json schema if the API supports it). Along with that, I’ve been working on a conversational memory middleware that automatically prunes historic irrelevant bits of the conversation transcript. I hope this keeps the model more steerable, but without loss of crucial details.

Thanks in advance for taking a look and providing any constructive feedback or ideas. Lastly, if you’re interested in contributing, please message me.

Comments URL: https://news.ycombinator.com/item?id=42470719

Points: 4

# Comments: 0

New comment by mackross in "Show HN: Graph-Based Editor for LLM Workflows"

mackross — Tue, 17 Dec 2024 10:06:15 +0000

Very cool :) can it just do observability too or do you have to use for all prompting?

New comment by mackross in "Inside the university AI cheating crisis"

mackross — Mon, 16 Dec 2024 06:09:34 +0000

We’ve built a solution in conjunction with a university to this problem that is pretty low effort to implement, but very few professors can be bothered to even try it out (the apathy and red tape is unreal). Honestly, it has been disheartening that distribution is so tough, as the results have been great for those who are using it.

New comment by mackross in "The Problem with Reasoners"

mackross — Wed, 27 Nov 2024 11:24:29 +0000

I love this — it captures what I’ve been struggling to articulate after using o1 a lot.

New comment by mackross in "A short introduction to Interval Tree Clocks"

mackross — Sun, 24 Nov 2024 09:06:35 +0000

I used these in a distributed sync in about 2013-2014. When Postgres got JSON support we ended up going centralized for that product and a simple logic clock was all we needed. Nevertheless, I still think they’re very cool.

New comment by mackross in "What's New in Ruby on Rails 8"

mackross — Tue, 08 Oct 2024 09:49:04 +0000

Still possible, propshaft works perfectly with the official js-bundling and css-bundling gems which let you add any js build pipeline as a build step