Hacker News: SOLAR_FIELDS

New comment by SOLAR_FIELDS in "The AI revolution in math has arrived"

SOLAR_FIELDS — Tue, 14 Apr 2026 12:13:34 +0000

Can get around this with a local STT model and use text input but UX is probably clunkier

New comment by SOLAR_FIELDS in "jj – the CLI for Jujutsu"

SOLAR_FIELDS — Tue, 14 Apr 2026 12:06:59 +0000

Every time I see a statement like this I wonder what specific features of git that people feel like are terrible enough that it’s time to completely start over. Besides “the UX is kinda shit and it’s confusing to learn”, which there are many solutions for already that don’t involve reinventing a pretty good wheel.

New comment by SOLAR_FIELDS in "Backblaze has stopped backing up OneDrive and Dropbox folders and maybe others"

SOLAR_FIELDS — Tue, 14 Apr 2026 12:02:12 +0000

Most have pointed out that the OneDrive exclusion makes sense due to its complexity. But I see no one here defending the undocumented .git exclusion. That’s pretty egregious - if I’m backing up that directory it’s always 100% intentional and it definitely feels like a sacrifice to the product functionality for stability and performance. Not documenting it just twists the knife.

New comment by SOLAR_FIELDS in "Show HN: Claudraband – Claude Code for the Power User"

SOLAR_FIELDS — Mon, 13 Apr 2026 04:00:35 +0000

What cursor has learned, very painfully, is that making a complex gui, even with the help of ai, is a lot fucking harder than a cli tool. Anthropic is wisely staying out of that space and sticking to more basic ui’s like cowork.

There is a LOT of work buried in your statement “all it would take”.

All one has to do is look at the evolution of cursor to confirm my statement. Compare v1 of cursor to v3 and see how much more insanely simplified the ui has become in v3 - it’s essentially a glorified cowork interface now

New comment by SOLAR_FIELDS in "The difficulty of making sure your website is broken"

SOLAR_FIELDS — Fri, 10 Apr 2026 23:30:10 +0000

You can always also simulate bad WiFi by walking away from your access point until you have bad wifi

New comment by SOLAR_FIELDS in "Sam Altman's response to Molotov cocktail incident"

SOLAR_FIELDS — Fri, 10 Apr 2026 23:25:18 +0000

Ha, I was giving an AI bootcamp to a room full of people and someone asked me my opinion of Altman. I hesitated for a second and replied that I would not trust Altman further than I could throw a rock about anything.

If Graham says this guy will always stop at nothing to get whatever he wants, which I absolutely believe, then why would you trust anything that comes out of a person like that’s mouth?

New comment by SOLAR_FIELDS in "I still prefer MCP over skills"

SOLAR_FIELDS — Fri, 10 Apr 2026 23:12:43 +0000

The auth angle is pretty interesting here. I spend a fair amount of time helping nontechnical people set up AI workflows in Claude Cowork and MCP works pretty well for giving them an isolated external system that I can tightly control their workflow guardrails but also interestingly give them the freedom to treat what IS exposed as a generic api automation tool. That combined with skills lets these non technical people string together zapier like workflows in natural language which is absolutely huge for the level of agency and autonomy it awards these people. So I find it quite interesting for the use case of providing auth encapsulated API access to systems that would normally require an engineer to unlock. The story around “wrap this REST API into a controlled variant only for the end users use case and allow them to complete auth challenges in every which way” has been super useful. Some of my mcp servers go through an oauth challenge response, others provide them guidance to navigate to the system and generate an api key and paste it into the server on initial connection.

New comment by SOLAR_FIELDS in "Sam Altman may control our future – can he be trusted?"

SOLAR_FIELDS — Tue, 07 Apr 2026 14:31:00 +0000

On the contrary, I very much care about what the other factions think because I want to know if things have already flipped and the easiest way to do so is just ask someone who's been using the tool. Of course the correct thing to do is to set up some simple evals, but there is a subjective aspect to these tools that I think hearing boots on the ground anecdata helps with.

New comment by SOLAR_FIELDS in "Sam Altman may control our future – can he be trusted?"

SOLAR_FIELDS — Mon, 06 Apr 2026 23:45:29 +0000

If you want to find an advocate for Codex that can give a pretty good answer as to why they think it's better, go ask Eric Provencher. He develops https://repoprompt.com/. He spends a lot of time thinking in this space and prefers Codex over Claude, though I haven't checked recently to see if he still has that opinion. He's pretty reachable on Discord if you poke around a bit.

New comment by SOLAR_FIELDS in "LLM Wiki – example of an "idea file""

SOLAR_FIELDS — Sun, 05 Apr 2026 19:52:05 +0000

Indeed, I have it open source, but want to preserve my anonymity here. The main gist of it is Quartz as a static site frontend bundle, backed by Decap as an editor, so that non technical users can edit documents. The validation is twofold - frontmatter is validated by a typical yaml validator library, and then I created markdown body validation using some popular markdown AST libraries, so there are two sets of schemas - one for the frontmatter, one for the body, and documents must conform via ci. I ship it with a basic cli that essentially does validation and has a few other utilities. Not really that much magic, maybe 500 lines of code or so in the CLI and another few hundred lines doing validation and the other utilties. It's all in typescript, so I use the same validation in Decap when people do edits.

New comment by SOLAR_FIELDS in "LLM Wiki – example of an "idea file""

SOLAR_FIELDS — Sun, 05 Apr 2026 07:36:22 +0000

I use a home baked system based on obsidian that is essentially just “obsidian but with structured format on top with schemas” and I deploy this in multiple places with ranges of end users. It is more valuable than you think. The intermediary layer is great for capturing intent of design and determining when implementation diverges from that. There will always be a divergence from the intent of a system and how it actually behaves, and the code itself doesn’t capture that. The intermediate layer is lossy, it’s messy, it goes out of date, but it’s highly effective.

It’s not what this person is describing though. A self referential layer like this that’s entirely autonomous does feel completely valueless - because what is it actually solving? Making itself more efficient? The frontier model providers will be here in 3 weeks doing it better than you on that front. The real value is having a system that supports a human coming in and saying “this is how the system should actually behave”, and having the system be reasonably responsive to that.

I feel like a lot of the exercises like op are interesting but ultimately futile. You will not have the money these frontier providers do, and you do not have remotely the amount of information that they do on how to squeeze the most efficiency in how they work. Best bet is to just stick with the vanilla shit until the firehose of innovation slows down to something manageable, because otherwise the abstraction you build is gonna be completely irrelevant in two months

New comment by SOLAR_FIELDS in "New laws to make it easier to cancel subscriptions and get refunds"

SOLAR_FIELDS — Thu, 02 Apr 2026 14:23:35 +0000

The thing is, it's so incredibly easy to make legislation that completely solves this. You just make a law that says "it must be as easy to cancel a service as it is to sign up for that service". Handles basically all edge cases, doesn't create misaligned incentives, and is very easily enforceable.

New comment by SOLAR_FIELDS in "Alzheimer's disease mortality among taxi and ambulance drivers (2024)"

SOLAR_FIELDS — Sun, 29 Mar 2026 12:30:39 +0000

The main question that comes up when I see a study like this is if they were able to take the same hypothesis and replicate it on another dataset in a different locale. For instance, presumably you could run the same study on UK data. Would we see the same results?

New comment by SOLAR_FIELDS in "I put all 8,642 Spanish laws in Git – every reform is a commit"

SOLAR_FIELDS — Sat, 28 Mar 2026 13:53:35 +0000

Perhaps reference it in the commit trailer?

New comment by SOLAR_FIELDS in "Nanobrew: The fastest macOS package manager compatible with brew"

SOLAR_FIELDS — Tue, 24 Mar 2026 15:05:10 +0000

Wow they are finally getting away from Ruby? Awesome. The speed will be a nice boon

New comment by SOLAR_FIELDS in "Nanobrew: The fastest macOS package manager compatible with brew"

SOLAR_FIELDS — Tue, 24 Mar 2026 15:04:19 +0000

FWIW this seems to have improved in recent years. Back in the dark times of non parallelized downloads I would purposefully wait to end of day and fire the thing off before leaving

New comment by SOLAR_FIELDS in "How I'm Productive with Claude Code"

SOLAR_FIELDS — Tue, 24 Mar 2026 05:42:19 +0000

To me commit volume and similar metrics are something that indicate ai adoption, nothing more. And for a lot of people right now that is the goal - however short or long sighted that it might be.

New comment by SOLAR_FIELDS in "Claude Code Cheat Sheet"

SOLAR_FIELDS — Tue, 24 Mar 2026 02:32:37 +0000

Claude is actually hilariously bad at knowing about itself. But if you have the secret knowledge that there is a skill on how to use Claude baked into Claude code you can invoke it. Then it’s really pretty decent

New comment by SOLAR_FIELDS in "Why I love NixOS"

SOLAR_FIELDS — Sun, 22 Mar 2026 17:46:04 +0000

Except if you go look at nixpkgs half of the technologies grandparent listed are either missing entirely or in a hilariously broken state.

The true answer is that there is just some software that is antithetical to the philosophy of nix. It’s not necessarily nix’s fault that this is the case, but their purism towards resisting opaque binary blobs going into the store reflects on the actual state of what’s available in nix.

You need some impure, nonreproducible way of managing that software. So on nix Darwin I let these opaque binary blobs manage themselves via homebrew and use nix for every other case possible

New comment by SOLAR_FIELDS in "Passengers who refuse to use headphones can now be kicked off United flights"

SOLAR_FIELDS — Sat, 21 Mar 2026 20:43:55 +0000

Yes. Because I'm asking the question who decides what is involuntary or not. Who is it? It seems like there is a presupposition here, but who is defining that?

Coming back to the Tourette's example: let's say someone starts shouting cuss words and loudly annoying everyone else "involuntarily". Do they get kicked off the plane? Why or why not? Who decides that? Does the person have to present medical evidence that they have Tourette's to not get kicked off the plane? If so, can they also present medical evidence of a condition that causes them to spontaneously press play on their mobile devices with no headphones and would that be accepted?

I'm obviously not defending the behavior of the loud-music-on-plane-players, or advocating that everyone needs to smell everyone's farts. I'm pointing out that this is something that is arbitrary and weaponizable.