I have been very curious to try Ohm. I'm currently using a hand-rolled parser combinator library, but Ohm looks slick. The online editor is nice too https://ohmjs.org/editor/

> The human is left doing whatever the machine can't, often a narrower slice of the original role

I haven't seen anyone talk about AI and its impact on flow yet. It's pretty easy for me to achieve a flow state while coding without AI, but with AI, I'm not so sure. I spend my time managing multiple Claude instances as they work on different tasks, and there's no time to go really deep into anything.

Flow was such a productivity boost for me. Even though Claude definitely helps me finish tasks quicker, I've started wondering how much quicker it actually is, vs getting into flow.

MBAs don't want to rely on people's flow. Let alone their skills. The fungible cog is their ideal.

I’ve tried having one “big” task that I’m focusing on with active back and forth while letting other Claude instances handle easier back-burner type tasks that it can effectively one-shot. But I’ve noticed that often turns into me spending more time/focus than I’d want on tasks that aren’t actually that impactful. I still think I get more done than I would otherwise, but I still haven’t found the best management strategy.

I’ve seen people share the same experience here on HN. Im also in the same boat while I find LLMs uncomfortably useful but quite tiring to work with. To maintain flow I spend more time on crafting a complete and clear promot, akin to programming in natural language and avoid the back and forth when possible.

I feel like you can get into a different sort of flow - a low-key flow where you're managing a bunch of different streams as interrupts come in. Different kind of focus, much more big-picture, kinda like playing an RTS.

IMO: That's just due to the speed of responses.

Hardware will continue to improve, and eventually you'll have the choice of reaching a flow state with 2026 models, or using frontier models at our current level of performance.

In a sense, that is almost exactly the vision of the future shown in accellerando. User can and does send tons of specialized agents into the world. I am still not certain if I buy the premise of the article, but then my company is too cheap to let me play with Claude.

At this point if I see "Made with {whatever_service_you_outsourced_thinking_to}" on a PR description and you didn't even feel like putting the effort to remove it, I'm going in with the assumption that you didn't bother to do or check a lot of things.

This is a piece I liked a lot about how to make coding agents better for flow state: https://haskellforall.com/2026/02/beyond-agentic-coding

https://news.ycombinator.com/item?id=46930565 - February 2026 (90 comments)

Some people think that flow is a negative. You do what you feel like doing, not what you should be doing.

Sounds like you’ve become a manager.

Very soon all software engineers will be managers. And no, not sarcasm.

I get into the same flow state as any fast paced strategy game like StarCraft.

This is very cool. Based on the title, I thought this would end with an example of using this font for code. I'd still be interested in seeing an example of that.

Good idea, but as several comments here suggest, the time when this sort of thing could be taken as satire is gone. I promise you there are multiple people here thinking that this is a good idea. I predict that within a year we will see a service that does exactly this.

The actual card is here https://deploymentsafety.openai.com/gpt-5-4-thinking/introdu... the link currently goes to the announcement.

I must have been sleeping when "sheet" "brief" "primer" etc become known as "cards".

I really thought weirdly worded and unnecessary "announcement" linking to the actual info along with the word "card" were the results of vibe slop.

Card is slightly odd naming indeed.

Criticisms aside (sigh), according to Wikipedia, the term was introduced when proposed by mostly Googlers, with the original paper [0] submitted in 2018. To quote,

"""In this paper, we propose a framework that we call model cards, to encourage such transparent model reporting. Model cards are short documents accompanying trained machine learning models that provide benchmarked evaluation in a variety of conditions, such as across different cultural, demographic, or phenotypic groups (e.g., race, geographic location, sex, Fitzpatrick skin type [15]) and intersectional groups (e.g., age and race, or sex and Fitzpatrick skin type) that are relevant to the intended application domains. Model cards also disclose the context in which models are intended to be used, details of the performance evaluation procedures, and other relevant information."""

So that's where they were coming from, I guess.

[0] Margaret Mitchell et al., 2018 submission, Model Cards for Model Reporting, https://arxiv.org/abs/1810.0399

To me, model card makes sense for something like this https://x.com/OpenAI/status/2029620619743219811. For "sheet"/"brief"/"primer" it is indeed a bit annoying. I like to see the compiled results front and center before digging into a dossier.

This looks super useful, but why hide your identity? There's nothing on the website about who you are and I notice you're using a new HN account.

I subscribed. Awesome idea and execution. Hope I see more apps working to make this stuff more accessible!

I feel like they are often unwanted discards... but we have one and we try to put interesting books in there. Recently gave away my entire Harry Potter series.

Someone has to stay to fight the shit happening in the US! The problem won't just go away if people move.

Heck yeah, so happy to see Anthropic fighting. This is what real leadership looks like. I'd love to see the same from Google and OpenAI.