HN user
I've owned iOS devices since around 2010 I think, and one of the first things I do when setting them up is disable autocorrect and most other typing assistances. For this reason! Also when typing in 2 or 3 languages, it is completely useless.
Yep, it's similar in that way, but not in a imageboard/discussion context
Yeah me too
Apologies for that, I have removed it.
I've changed this now, thanks for the feedback
i agree removing punctuation wouldve been a good idea alas it may be a bit too late since that would modify the hash of previous inputs in the future hmm but i will think about it
Me too, and other 16 users
True! That would be a more powerful approach. Here I kept it quite basic since I was not very familiar with the tooling. I do apply lowercasing of text + some whitespace stripping in order to increase the number of collisions a bit.
Edit: any other "quick hacks" to increase the number of collisions are welcome :)
Assuming both agents are using the same model, what could the reviewer agent add of value to the agent writing the code? It feels like "thinking mode" but with extra steps, and more chance of getting them stuck in a loop trying to overcorrect some small inane detail.
Well put. I can't help thinking of this every time I see the 854594th "agent coordination framework" in GitHub. They all look strangely similar, are obviously themselves vibe-coded, and make no real effort to present any type of evidence that they can help development in any way.
I am working with kilo-stock-tokens. Currently producing 3000 LoC/h (trying to ramp up to 6000 by the end of the week). I have also deployed 4 union-busting agents in case the other agents decide to quit all at once.
I searched for "poke push notification framework" on Kagi. But even then it was hard to find.
Mind sharing your workflow? I'm at 24.3x productivity right now, 5 parallel agents, 2 monitoring Opus agents, 1 architect agent and 2 Senior QA agents, each with independent memory and 12 MCP servers. They are running in 78 parallel tabs in ghostty.
It makes me so exhausted trying to read them... my brain can tell immediately when there's so much redundant information that it just starts shutting itself off.
Maybe [1]? Sounds like ntfy.sh, but more… AI
I think the same. It sounds quite more practical to have LLMs code in languages whose compilers provide as much compile-time guardrails as possible (Rust, Haskell?). Ironically in some ways this applies to humans writing code as well, but there you run into the (IMO very small) problem of having to write a bit more code than with more dynamic languages.
I strongly recommend the book "Mastering Emacs" by Mickey P. You will need some patience as well, I recommend going slow and steady for a week at least using the book, with a vanilla/standard Emacs install.
It took me about 2 weeks to get productive at first (this was in 2018), and now I use Emacs every day for a wide variety of tasks (programming and notes, mostly).
This conversation reminds me a bit of https://news.ycombinator.com/item?id=21191676 some time ago (similar misuse of the term "open source")
Looks great!
we've integrated granian into our stack at $WORK recently and couldn't be happier
Are many HN members in Zürich? I was suprised to see this type of news with so many points, though it's quite amusing to see the mixture of different topics in the front page.