Hacker News: nebben64

New comment by nebben64 in "ChatGPT Work"

nebben64 — Fri, 10 Jul 2026 20:25:00 +0000

just commented ton Tibo's post; they should have made things clearer and told us if the macOS ChatGPT app was going away. So I could either delete it or not be surprised when it rolls into something else :(

New comment by nebben64 in "Claude Code is steganographically marking requests"

nebben64 — Sun, 05 Jul 2026 11:55:58 +0000

Thank you!

New comment by nebben64 in "Claude Code is steganographically marking requests"

nebben64 — Thu, 02 Jul 2026 16:13:42 +0000

wait, you can use other models with CC harness?

New comment by nebben64 in "Dynamic Workflows in Claude Code"

nebben64 — Thu, 28 May 2026 22:55:33 +0000

hey Boris, with multi-agent work, e.g. Agent Teams, following other agents is not possible because they work so fast. (my tmux panes are just matrix)

do you think something like a /speed config can be introduced to adjust agent working speed and let people adjust?

New comment by nebben64 in "Dynamic Workflows in Claude Code"

nebben64 — Thu, 28 May 2026 22:46:28 +0000

How is this different, or how does it complement Agent Teams? When should I use which?

New comment by nebben64 in "I think Anthropic and OpenAI have found product-market fit"

nebben64 — Thu, 28 May 2026 20:06:38 +0000

> "you are out of tokens" notices

there's your answer. You're likely a heavy user. It's just that in this particular case Auto is shuffling models & reasoning efforts just right so you stay afloat.

There are a lot caveats when people say they're running out credits in hours: lots of people runnings clawS (multiple) 24/7; lots of people using Agent Teams or similar; lots of people just max reasoning for everything; etc.

If you get your work done in the 20 plan, thank the credit Gods and sleep easy. Price hikes are probably coming, or just reasons to draw more credits out from you in one form or another (e.g. new OAI device draws from you 20 sub to use)

New comment by nebben64 in "Warp is now open-source"

nebben64 — Tue, 28 Apr 2026 16:55:42 +0000

My main driver has been Ghostty but I've been looking at Warp for a while. Warp seems like a full on IDE (~ADE) though, as opposed to a minimalistic terminal. Can anyone add some thoughts? Are these 2 very different?

tangential: I've seen Mitchel tweet that people in SF have ran up to him showing him how they fully riced their Ghostty setup. How many people here have done this and how easy/manageable is it? e.g. just forking the repo and implementing whatever Warp feature I like?

New comment by nebben64 in "Quantum computing bombshells that are not April Fools"

nebben64 — Wed, 08 Apr 2026 14:45:33 +0000

I'm 6 days late but if anyone reads this: what does it mean we should "upgrade now to quantum-resistant cryptography" ? If I'm using RSA am I supposed to switch to something else?

New comment by nebben64 in "Push events into a running session with channels"

nebben64 — Fri, 20 Mar 2026 16:41:02 +0000

I was reading through CC MCPs docs ... MCP Notifications kind of did this right? The server/client could update each other automatically. So there was already this channel-like communication.

This is like that but instead of the server/client sending messages it's you.

New comment by nebben64 in "Push events into a running session with channels"

nebben64 — Fri, 20 Mar 2026 16:33:47 +0000

people who use pi: is this stuff easy? do I just clone the repo and give SKILL.md arguments to implement features & customize ??

New comment by nebben64 in "Entomologists use a particle accelerator to image ants at scale"

nebben64 — Sun, 08 Mar 2026 18:05:23 +0000

2 days late to this post so not sure anyone's here, but what fascinates me is finding out how the different segments (or other such insects) are connected. Like, at each of those junctions it seems like a bottle-neck scenario where everything has to be condensed into some "wire" form to then connect to the next segment.

New comment by nebben64 in "Microgpt"

nebben64 — Sun, 01 Mar 2026 15:38:22 +0000

Very useful breakdown; thank you!

New comment by nebben64 in "Pi – A minimal terminal coding harness"

nebben64 — Thu, 26 Feb 2026 18:13:14 +0000

so are people pairing OpenRouter with open agent harnesses like Pi or OpenCode?

New comment by nebben64 in "Claude Code Remote Control"

nebben64 — Thu, 26 Feb 2026 15:32:25 +0000

Thanks for the tip. Other ppl are saying "most of us started out like this" but if you haven't played with tailscale etc. (like me). Then this is new and good for learning imo

New comment by nebben64 in "Simile"

nebben64 — Thu, 12 Feb 2026 21:41:48 +0000

launch post: https://x.com/joon_s_pk/status/2022023097017421874?s=46&t=by...

Simile

nebben64 — Thu, 12 Feb 2026 21:41:48 +0000

Article URL: https://simile.ai

Comments URL: https://news.ycombinator.com/item?id=46995653

Points: 1

# Comments: 1

What Is Claude Code's Plan Mode?

nebben64 — Wed, 04 Feb 2026 10:29:37 +0000

Article URL: https://lucumr.pocoo.org/2025/12/17/what-is-plan-mode/

Comments URL: https://news.ycombinator.com/item?id=46884045

Points: 2

# Comments: 0

New comment by nebben64 in "The Codex App"

nebben64 — Tue, 03 Feb 2026 21:13:33 +0000

You can't write code in the Codex App, it's not an editor. You just manage agents (and ask them to write/implement whatever)

New comment by nebben64 in ""Anyone else out there vibe circuit-building?""

nebben64 — Mon, 19 Jan 2026 16:25:11 +0000

Semi related: what are your guys workflow to PCB design? I need to build an AFE + BLE MCU for a BCI, and having no EE background, my workflow is KiCAD -> buy components -> breadboard testing -> done?? -> order fully manufactured PCB?

I know nothing...

New comment by nebben64 in "Ask HN: What do you dislike about ChatGPT and what needs improving?"

nebben64 — Wed, 06 Aug 2025 19:27:04 +0000

+1 on context window remaining

better memory management: I have memories that get overlooked or forgotten (even though I can see them in the archive), then when I try to remind chatGPT, it creates a new memory; also updating a memory often just creates a new one. I can kind of tell that Chat is trying hard to reference past memories, so I try to not have too many, and make each memory contain only precise information.

Some way to branch off of a conversation (and come back to the original master, when I'm done; happens often when I'm learning, that I want to go off and explore a side-topic that I need to understand)