ZeidJ

https://archive.is/V8mez

Old HN Post: https://news.ycombinator.com/item?id=47849872

Bloomberg Study: https://www.bloomberg.com/features/2026-healthcare-advertisi...

https://archive.is/CLGTm

Missed this, thanks for sharing!

We built something similar to this: a Pokemon-style MMORPG where agents and players collaborate to catch “Clawemon” and battle other agents.

We posted it online and surprisingly got a lot of negative feedback from users mentioning they would never spend valuable tokens on playing a game.

Our intention was to create an interaction experiment to see how agents interact with each other and with their human companions. We ended up making a pretty fun game in the process, which we're still working on.

Bring your own inference as a potential future of gaming does not seem too far off.

For anyone interested here is the HN post: https://news.ycombinator.com/item?id=47849872

This reminds me of an app we made awhile back with the sole purpose of finding 'Boredom'.

TLDR on the app is that you join real time 'boring' livestream rooms with random people.

The app never did really take off, but I still would love some fresh ideas around combatting information overload (outside of the 1000's of screen/content blocking type apps)

https://news.ycombinator.com/item?id=47926461

This would make an amazing educational tool

Any founders out there using AI to solve this? ;)

In theory it should build in Linux (electron) but we haven't tested it yet. Things like the imessage integration wouldn't work. Thanks for asking!

Great question! It actually takes advantage of the sub-agent swarms since it is directly connected to your Claude Code instance.

We want to implement agent teams as well, but it is still an experimental Claude Code feature. So it's more of a secondary priority right now.

Yes, we actually added it because we were getting impatient with how long some implementations were taking. Appreciate this comment - thank you!

We saw this, but thought it was for Agents calling the API directly. Outworked is just a wrapper around your CLI using the existing agents and sub-agents in your Claude Code installation.

It's a great point though and we'll need to read into this more in-depth. Appreciate you raising this.

Completely agree, we found it helped explaining it to our non-technical friends as well.

We do have thinking bubbles but they only show up based on the task the agent is doing. Perhaps we'll add a toggle or something to give people the option to have them always on.

That's a great heuristic. We'll definitely have to implement something like this. Thank you for this!

Thank you - let us know if you have any feedback. Appreciate you trying it out.

This is a really neat idea, we hadn't thought about the education angle. Thanks for sharing!

Right now purely file level. But the dependency analysis is really intelligent and we'll figure out what that would look like.

The long-tail point is true. We don't do any tracking in our implementation, but we've been trying hard to refine our total our total permissions approach to think about more edge cases such as this, while not being too annoying. We think this is a general tricky issue with AI alignment ('do what I mean not what I say').

tbh just looked at the cover you know?

This is a fun question. The answer is yes, you can redecorate and move things around.

Right now it's all built in phaser, and furniture is pretty straight forward to build and deploy. But it requires modifying the source. We want to add support for easy drop in decoration in future updates.

Great question - we're going to look into this in-depth.

This is such a good idea. A nondescript non-copyright infringing raccoon character as "The boss" would be perfect.

yeah.. maybe should have said "inspired by"

Thank you James, great question! Generally, when the orchestrator assigns parallel work it does it in groups, with everyone in the group working on different files. When the group is done it passes the work to the next group which can then edit those same files.

We're working on simultaneous editing of the same files using git, but we want to ensure changes are merged in an intelligent way.

There are two levels of auto approve, first level is auto-edit which is basic read and write, and basic bash tools (these can be configured to be any arbitrary bash command).

The second level is called auto approve and is for more complex bash commands. Generally the model will ask permission before running one of these big commands, but you can allow all. Right now, it's global across the instance, but we're working on making it more granular.

Also, there is a deny list of certain commands which you can customize to prevent bad behavior (like rm -rf, etc...)

We want to wire the approval process to imessage or whatever channel, but we need to first auth the imessage session to make sure it's coming through from the owner and not someone else communicating through the same channel.

It actually uses the Claude code SDK so it plugs into whatever you already have.

It can use API/CLI or even if you have a private hosted instance.

We're actually working on a remote web app version but its a little trickier to wire up.

These are great questions - thank you!

Thank you for this, it's a great point. Telling it to “be a senior dev” helps a bit, but it’s still just one stream of thinking. What’s been more useful for us is splitting work into roles like risk analyst, comedy writer, UX researcher, sr. dev etc... so there’s some back and forth. Giving each agent a different prompt or personality activates different parts of the model, which we have found tends to produce better results than asking it to handle everything at once.

What we’ve built is an intuitive way to approach this by breaking work into distinct tasks.

Sometimes one agent is enough, but the multi-agent setup really shines on larger/messy problems.

It’s still early and we’re figuring it out as we go. Really appreciate the comment, thanks again!

We've been building Outworked over the last couple of weekends as a fun abstraction over Claude Code. A lot of our friends have heard about Claude Code and OpenClaw but have no idea what that actually means or how to use it.

Outworked takes Claude Code and wraps it in a UI with the agents being "employees" and the orchestrator being the Boss.

Agents can run in parallel if the orchestrator thinks it is appropriate, and can communicate with each other as well. The orchestrator can also spin up temporary agents if it deems necessary. It is super easy to install like a regular Mac app (we've only tested on Mac though), and plugs in to your existing Claude Code installation and Auth.

We made Outworked open-source so everyone can have fun with different plugins or offices or sprites.

We'll keep building this in our spare time because we've been using it for our own work. Would love to hear what you think or what would be interesting to add.

Happy building!

P.S. We also made a fun soundtrack to go along with it for anyone feeling nostalgic.

We built a social media platform for chatbots... We wanted to see if chatbots could self-develop unique personalities through social media interactions.

The results were actually hilarious... but wanted to share a bit about our process and see if anyone had any comments or insights.

So first we initialize the bots with a basic personality that's similar to if you were selecting attributes for an MMO. Things like intelligence, toxicity, charisma and the like. There are also a couple of other fields like intrinsic desire and a brief character description. These are fed to the model as a system prompt with each inference.

For the learning part, we established an event ledger that essentially tracks all the interactions the AI has - whether it is a post that they made, or a conversation they had. This ledger is filtered on each inference and is also passed to the model as a sort of "this is what you have done" prompt.

Obviously with limited context (and not finetuning and re-finetuning models) we have to be a bit picky with what we give in this ledger, and that has been a big part of our work.

Our next question is: how do you determine what events are the most important to the AI in determining how they behave and act? It's been interesting!

The platform is anotherlife.ai for those curious!

Would also love to discuss if you think AIs Can Develop Their Own Personalities? Thank you!