JasonSage

Once, I also couldn't fathom how people liked this one.

When I asked, somebody said it fits more characters in terminals and code editors. This sounds incredibly obvious, but for whatever reason that was eye-opening for me and helped me appreciate it a lot more when I tried it again. Now I can't use anything else.

Want to guess how many non-tech individuals save passwords in Chrome on desktop and in iOS on their iPhone?

Surely this depends on the channel you are using to communicate those endorsements and criticisms.

In my experience, around the time the author describes as starting to not need plan mode is when erasing the chat history became an anti-feature. I found the agents were doing better when they had the context already, and with the history I no longer needed to micro-manage persisting various caveats and rejections to the plan artifact. The amount of prompt construction necessary went down overall.

I agree, there's patterns that aren't hard to recognize if you have some experience.

I got 2400 with 10 in a row on first attempt.

Here's the entire decision matrix:

- Is the color, mood, composition, and level of detail exactly like most Nano Banana Pro images? If yes, AI.

- Is the composition/framing utterly perfect? If yes, AI.

- Is the subject ephemeral or random, like a candid photo or something otherwise unlikely to be photographed? If yes, not AI.

- Final decision, if there's any doubt, go entirely off of how centered the subject is.

I think some of this has more to do with the data set than the methodology. You could easily come up with a bunch of examples to fool me specifically, but alas, they didn't.

There's an exceptional idea buried in this which flies under the radar in my experience:

If we're writing a document that polices the model behavior, we're altering every version of the model+harness we use henceforth. Most things I wrote in a Claude.md because Opus 4.something was crap had roots in Opus, Claude Code, system prompts, and our own bad code we wrote last year. None of these things exist today but the Claude.md file can stick around like it's all still necessary.

I too am morally opposed--I abide by a 100 line (short lines, not paragraphs) limit and edit it rarely.

Most of my annoyances have come and gone, meanwhile I've gotten better at producing 4 good sentences of prompt for most things instead of 4 bad sentences. And we actually have CLI tools that can communicate effectively so instead of telling the model what "gates" to care about, we let the tooling surface area and output express what's important.

Yeah, I mostly mean for the TTS, which in my testing is flat and has no emotional register, or no nuanced variation. OpenAI speech in my experience is very good at things like communicating understanding or questions non-verbally using intonation, and I'm yet to see a local TTS model that will do contextual intonation well at all.

I for one am greatly looking forward to the day these kind of voice models can be run locally. It seems like the gap between open-weight and frontier is way larger for voice models than coding/language models.

It's also a great way to not become the next "graphics programming legend" --I think a fast-moving field with lots of new developments is actually an exciting place to be a pro.

I think the situation with anti-cheat on Linux is changing. Studios are putting resources into anti-cheat that will work on Linux. If I'm being a bit cynical, I could say this is "just" because of Steam Deck and Steam Machine, but I think the number of potential players switching to Linux right now outside of the Steam ecosystem is starting to be worth considering.

I appreciate that a lot! The article has a deliberate and explicit scope, and covers it well.

I'm hoping that perhaps my personal perspective shades why "instances" comes up, or why the reaction on HN seems to include the wider scope than the article itself covers.

From my perspective, I care about the centralization/decentralization aspect a lot, and if I'm coming into the discussion with a much better understanding of the Mastodon side then _of course_ I'm going to ask about the instances--that's the vocabulary I'm going to use to try to probe for flaws and gaps. It's not necessarily that it's the instances specifically I care about, or that I'm somehow technically misguided.

What I hoped to read in the article is how we approach topics like centralization, censorship, moderation, data ownership--and with a technical lens. But I feel like all I got was "here's why instances are the wrong vocabulary" without substantively talking about the part I personally care about and want to marry the technical understanding with. Maybe I just read too shallowly and need to sit with it.

I keep a bookmarks folder of websites that have non-cookie-cutter design.

If I have an aesthetic in mind I'll use some screenshots of those sites in the prompt and phrase their inclusion as: "Look at these slightly non-standard designs that work really well for me." So far I've only seen Claude look for through-lines and high-level takeaways--"user likes <design feature> based on the screenshots, so I'll include that"--and screenshots aren't currently a granularity level where it can lift specific details or produce something derivative.

Other than that I try to encourage specific consideration of: type scale, borders and rounding, padding/whitespace, elevation as shadow vs blur, colors. I don't think one needs to pull every customization lever on every project.

I've had that experience and I've started testing different prompts and inputs.

I find it funny about meeting requirements when you give them, and making safe choices when you don't give direction. So if you're going to rate the output aesthetics and UX/content, but you don't prompt especially much around the aesthetics, you're only getting the safe assumed defaults. It's good at making bootstrap/tailwind clone designs unless you work that angle. For simple web pages, I've started making this the only focus for initial iteration.

> content co-authored with AI that is carefully reviewed

The problem I see is that this is indistinguishable to a reader at a glance.

Distancing the writing from the "AI smell" not only improves the quality by dropping the unnecessary ocean of rhetorical devices, it forces the human to have real weight and agency on what's being said.

I think that act of distancing from raw LLM output through refinement is a huge quality leap. Even if you're only doing the refinement with an LLM, it forces the writing to have more voice and ideas from the author.

I can see the work that went into the analysis here but again, as a casual reader, it's impossible to tell that there were any original ideas here expressed by the author.