Hacker News Reader

Comment by dannyobrien | Hacker News Reader

What I'm looking for right now is a tool like this that lets more than one person participate in the conversation: right now Claude Code and similar tools are great for working alone, but I'd like to effectively pair-prompt with a partner who can see what's happening, and take turns steering the conversation.

Can Rowboat do this? If not, does anybody know a harness that can?

View on HN

Disclaimer: I'm part of the team building it

That's what Amp is built around!

By default conversations are shares in your team (you can also make them private), and the agent has access to them.

So you can do things like "how would $teammate think about this" and the agent will read your colleague's conversations with Amp to get a feel for that and evaluate your work based on that.

Or just figuring out what everyone is doing at the moment is much easier that way

I have a hunch that both OpenAI and Anthropic are building towards this very quickly. It's one of the startup ideas that will be killed overnight when it's "officially" launched. Claude Tag was just released which lets Claude participate in chats in Slack - only a matter of time until they move those chats out of Slack and into their own platform.

That hunch is probably right - the labs are likely building towards this. However, our bet is that in knowledge work the labs don't have a structural advantage: the model isn't the product there, unlike coding where it mostly is - and even in coding, opencode and others are gaining real traction.

What they do have is funding and distribution, but that's the same advantage every incumbent has against every startup.

The single biggest advantage we have is that the labs are tied to their ecosystems. Claude still doesn't have image generation; Gemini-flash-lite is the best cheap model, but Gemini's apps can't use the latest models from Anthropic or OpenAI. We can always use the best tool for each job.

I've heard that refrain ("we can switch models so we won't be obsolete!") a hundred times, but it doesn't hold any water for me. OpenAI and Anthropic command such a large percentage of LLM usage that it doesn't really matter which one implements your product - either way, you're screwed.

Your end users literally do not care what model you use behind the scenes or if you're using "the right tool for the job".

> Claude still doesn't have image generation

What? It has for years. Go ask it right now.

Just did - asked Claude Opus 4.8 in Claude Desktop to generate an image of a horse. It drew an SVG by hand in code and said (verbatim): "I drew it by hand in code, not with an AI image generator. There's no diffusion/photo image model wired into this session."

On the labs: agreed that end users don't care about the model - only that the job gets done well, which is our argument too. At any point some model is best at a given job, so any single lab is behind for a portion of time on a portion of tasks.

Oh snap, you're right that Claude can't generate images. All of these chat interfaces blur together in my head these days haha

I seem to remember GitHub working on something similar. I remember having seen a video from a conference talk someone at GH gave at an European AI conference a while back. She presented some current prototype/early version they were working in. Where AI was basically like a team member in a chat interface with access to the task boards, issue tickets and also the whole conversation of the team, if I remember correctly.

Also different members of the team could steer/approve what the AI did or did not do.

Ahhh found the talk: https://www.youtube.com/watch?v=ClWD8OEYgp8

Not yet, but we're actively working exactly toward this - group chats with the assistant, where people can see the session and take turns steering. We're exploring a peer-to-peer connection for it so there's no server in the middle, which keeps it consistent with the local-first setup.

I built a harness in the cloud with slack like interface for this, allowing multiple people to join. It allows chat members to tag action items, work on files and sync to GitHub. My team uses it to coordinate on our task and teM context together, setup meetings which are auto transcripted and ingested into the attached wiki, and connect to calendar to setup meetings. Built it for our needs.

Didn't really consider putting it out in public. Is there a viable product out of this? How much would you pay.

Have you tried using a purpose built pair programming app? Essentially these are tools with low latency screen sharing and remote control. Then you can pair-prompt in a call.

Zed's original reason for being was collaborative programming

https://zed.dev/docs/collaboration/overview

Not sure if the agent stuff is shared in the "channels", though.

This isn't exactly what you're looking for but for just the coding part, I am working on https://www.buildautomaton.com to allow multiple people to participate on a shared coding session. It's also bring your own agent subscription, uses ACP to talk to any agent (Cursor, Claude, Codex, etc), and is end-to-end encrypted for most of your IP.

Looks great, but the pricing model is a challenge for a small team. If there was a generous trial period (for testing) with a lower small team price I might be able to consider it, but it’s hard to justify constantly increasing AI and compute costs (already paying for several model subscriptions, existing orchestration tools… in addition to typical infrastructure)

Thanks for the honest feedback. I'm still playing around with the pricing and trying to get it right.

Rather than a single application, is it possible to run a VM and have multiple remote access sharing one login session?

I get that great pains have been made to make sure that doesn't happen by default. But if you really want to co-op on something, why not at the session level on a dedicated VM/login pair?

Today the UI and the server run as a single app. We're working on separating that, so you could technically have one server with multiple clients. But even then, for collaboration with others, there are two issues with sharing a login session: (1) the system doesn't know these are two separate people, and (2) it has access to someone's email etc. - if it doesn't know who the user is, everyone gets the same access and can run anything.

That's why we're exploring a peer-to-peer setup for group chats instead. Each person keeps their own machine and data, and the assistant knows who's who and can ask the primary user for permission if the secondary user wants to run something non-trivial.

Haven't tried them but there are ways to wire a coding agent to slack, that gives you a multi-user session right there doesn't it?

Or you could use tmux and a shared login and any tui agent harness.

Obviously they would be very flawed but a place to start.

You might want to take a look at AionUI. Its a desktop app. I was an early contributor there and they do seem to work on like AI collaborations conversations rather than a single user only chat.

I use a tool called linzumi for this

...tmux?

Reply on news.ycombinator.com