Hacker Newsnew | past | comments | ask | show | jobs | submit | contextfree's commentslogin

Someone on Twitter dubbed it the "agentic ick"

It's really funny that it uses the Windows dotted-line focus rectangle as a stylistic signifier of "Windowsy thing" while having no idea what it's for.

Heh well there was a dashed border in the "original" version and I suppose it just made it the windows-y equivalent. I imagine it wouldn't have done the same if it was prompted from scratch.

("it" being Opus 4.8 btw)


JS async is similar to C# async (which I think it was based on), think lots of developers are familiar with one or both of those. As one of those developers Rust async definitely threw me for a loop (literally?) when I first encountered it.

fwiw, I gave it the same vibecoding project I'd previously tried with Sonnet 4.5 and it took Fable 2 hours to go well beyond (like, 2x beyond) where I got in 8 hours with Sonnet 4.5. (beyond that idk, because past 8 hours with the Sonnet 4.5 version I hit the "vibe limit" where it becomes easier to just write/edit the code yourself than get the agent to do what you want; and past 2 hours with Fable I hit my usage limit.)

Addendum: Interestingly, it ended up taking me about the same amount of time - 8 hours or so - to hit the "vibe limit" with Fable. But in that amount of time I made about 5-10x as much progress. So my feelings are:

1. It's exponentially better

2. yet, somehow, hand coding still isn't dead, at least for me


How many $ do you guys spend when your session runs for 30min? What's the total budget?

I just have a regular Claude subscription and keep within its usage limits

But isn't running Claude models for 30min expensive? Or is Claude Code not expensive?

I use Cursor and if I ran Claude models for 30min I might exhaust my mobthly budget! Maybe it's an API billing issue though


It's included free with subscription plans until June 22. I get about 2 hours a day of usage through Claude Code until I hit my usage limit. I just use it for 2 hours then wait for the next day.

It seems ridiculous that, for example, Copilot running in Visual Studio working on a C# codebase finds stuff in code by grepping around instead of using the Roslyn-driven code symbol and semantic database built into Visual Studio. I'm guessing it's because the people they get to work on AI stuff are AI People who probably only write in Python

It is sort of funny when Copilot hasn’t been integrated with Microsoft’s stuff. But it does make some sense from a business point of view. Make it work with grep, it works everywhere.

Microsoft was mostly on the Embrace step. They've reached the Extend step with Copilot. They'll eventually Extinguish grep.

It's best not to use Microsoft products.


What does this even mean, how do you extinguish grep

Same way you extinguish _wget_ and other commands, by replacing with an alias [0].

Microsoft had to replace _powershell_ with _pwsh_ because of the anti-consumer aliasing they did. My powershell profile is full of all the commands to remove those aliases.

Last time I check, Microsoft even creates a python alias to bring up their store vs calling the exe in your defined path that was manually installed.

[0] https://www.educba.com/powershell-wget/


There's a lot more examples of grep usage than Visual code search in the training set.

Codex does this in VSCode as well.

Compilations break all the time and those symbols either become useless or it’s just quicker to use grep.


What in file explorer is still web tech based?

This was a feature in Windows 10 preview builds for a while (2018-2019ish iirc) but it never shipped to retail.

A fundamental problem with this is that "8" is two different releases (8.0 and 8.1), "10" is about 9 different releases, and "11" is three different releases so far (21H2, 22H2, and 24H2). It doesn't make much sense to lump all of them together because they share the same marketing name; technically there's no difference between going from 8.0 to 8.1 or from 22H2 to 24H2 and going from Vista to 7 or 10 20H1 to 11 21H2


It's called Global Tetrahedron but it has a dodecahedron as a logo/emblem (guessing intentional)


Yes, and English/natural language is not necessarily more concise than programming languages, if you need to describe something precisely.

For example, I was recently trying to get an agent to debug something which was difficult to debug because it ran in an exotic context, where debuggers and logging and printf couldn't easily reach. The agent kept coming up with more and more elaborate and smart-sounding theories and debugging strategies, but nothing worked. I stupidly kept going with this for like 20 minutes, until finally I just went into an IDE, did a simple "comment bisection" where I commented stuff out until I found the line that was breaking, and found and fixed the problem in five minutes. So I solved it by typing code. The code I typed: "//" (in about six places). I could probably have gotten the agent to do the same thing but would have actually literally had to type more to explain to the agent what I wanted. In fact it took me longer to write this comment describing what I did here than it did to just do it.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: