Live data from Hacker News

Viewing profile — parsak

parsak

HN member
Joined
Fri, Apr 07, 2023, 8:25 PM UTC
HN karma
2
Public activity
19 items

About parsak

No profile information was provided.

Recent public activity

  1. comment
    Comment #47442573

    the two-plane idea here is really interesting -- separating long-lived planners from short-lived workers is a clean mental model. curious what happens when you're on windows though…

  2. comment
    Comment #47442291

    the way i handle it in pane: every pane is one worktree, and the diff viewer + keyboard shortcuts (squash, rebase, merge) are right there before you ever push. so the review step i…

  3. comment
    Comment #47442244

    i built this because i was running claude code and cursor on the same repo and they kept overwriting each other's files -- that sentence is exactly what motivated pane too. git-lan…

  4. comment
    Comment #47442230

    the "containers manually vs compose" framing is exactly right -- that's the coordination layer that's missing from raw worktrees. one thing i'm curious about with chatml: how's the…

  5. comment
    Comment #47442201

    the persistent markdown approach to context drift is clever - treating state files as a first-class primitive rather than hoping the agent remembers between sessions is the right i…

  6. comment
  7. comment
  8. comment
    Comment #47442175

    the "45 minutes watching one agent" framing is exactly right - the serial bottleneck is the real problem, not the model. one thing worth thinking through as shard matures: the mana…

  9. comment
    Comment #47404759

    Cool concept with the Blueprints system - defining agent teams declaratively is a nice touch. I'm building something adjacent called Pane ( https://runpane.com ) that comes at it f…

  10. comment
    Comment #47404753

    The auto-snap detection is clever - automatically splitting when it detects an agent CLI is a great UX decision. I took a similar "own the terminal" approach with Pane ( https://ru…

  11. comment
    Comment #47404724

    Nice work! The at-a-glance status monitoring is a great idea - the "what are all my agents doing right now" problem is real once you're running 4+ sessions. I'm working on somethin…

  12. comment
    Comment #47279528

    Here's a more in depth writeup on the workflow: https://www.runpane.com/blog/ai-native-development-workflow

  13. comment
    Comment #47279230

    Oh, arguably the best part (which I forgot to mention) is that our terminals continue running in the cloud, so dev work isn't blocked by our computers going to sleep.

  14. story
    300 Founders, 3M LOC, 0 engineers. Here's our workflow

    My co-founder Tyler Brown and I have been building our product for 6 months. The co-working space that Tyler founded that we work out of houses 300 founders that we've gleaned agen…

  15. comment
    Comment #47278828

    Fair enough - with that said - be mindful of the times. I am pretty deeply involved in Seattle's startup scenes and a notable startup recently laid off 35% of its engineers, and ma…

  16. comment
    Comment #47278810

    glad you feel the sentiment :) any in particular you recommend?

  17. comment
    Comment #47278805

    Fair enough, I spend a maximum of 200 a month given I use the MAX plan from CC. I don't find myself every hitting the weekly limits - but recently I've gotten close!

  18. story
    Is anyone else drowning in terminal tabs running AI coding agents?

    I work on a 300k line monorepo, just me and my co-founder. At any given moment I have 3-6 CLI agents (Claude Code, Codex, Aider) running simultaneously across git worktrees. The th…

  19. comment
    Comment #42605568

    I wonder if you could make a workflow like this run well completely local. I might try to build it. I saw this fully local open source tool recently that helps categorize your phot…