Does anybody mind explaining how the web of articles in the first image helps the writer?

The honest answer is it doesn't help a ton, at least not in its current form. It's fun to look at, and occasionally I'll see some interesting semantic connections between articles - but by far the more useful tools here are the wiki generation, auto-tagging, and chat/MCP features. The graph view definitely needs more love - if anyone has thoughts on how to make it more useful, I'd love to hear them.

My first thought is that this would be a great place to find new topics of interest at the "overlap" regions.

FOMO is making me feel like I should mess around with openclaw but I can’t see any use cases that I can’t accomplish with other tools. What should I do based on this article?

Don't just do something, stand there!

Like investing in index funds, a big part of it is psychology of the individual as Jeeves would say.

Find a way to scratch the FOMO itch without taking on too much risk.

I recommend going to the pub with some friends and having a chat about anything that isn't work.

Nice blog btw

Why do you need a reason to try anything?

Just go out and prove how useless it is. If, during your testing, you find that it has no good use case, toss it.

Waiting for others to validate a tech for you is a mistake IMO.

How else can you be in the right place and right time to discover a problem to solve that can’t be seen from afar?

Interesting to see it took them so long to implement this. Claude was super limiting without the ability to have a scheduler or a connection to events

Thank you for sharing. This looks nice.

Do you have any further plans for this project?

just continuing to build on it for fun, adding various features as i could think of!

"Nobody caught it in review" and "they're in someone's head" sound like issues to work on.

Some todos that come to my mind:

- Review more thoroughly.

- 'Vibe code' some unit tests

- Document and communicate the things that are in team members heads that should be openly shared

- Review more thoroughly -> easier said than done if you want to keep velocity - 'Vibe code' some unit tests -> yep, we do that - Document and communicate the things that are in people's heads -> agreed, that's the hard part in practice :/

How does this compare the building your own bot that has access to these tools: - web plugin - api access to messaging - access to a job scheduler

This has been my approach and of course what you lose is the "random and surprising" (maybe good) but also the "evolutionary" aspect.

So, if you write strong tooling (even with AI) around the connection points - you can create blackboxes tht are secure and only allow the agent to perform certain actions. The blackbox email service calls out to a secure store (for keys/etc) and accesses your emails in a read-only way, etc (for example).

Everything is then much more intentional. You're writing tools for your agent but you also can't do fun or evolutionary things which is most of the fun behind OpenClaw. That and many people seem to genuinely see them as 'pets' or 'strange Ai friends' but that's a different problem and it's due to the interesting methods OpenClaw uses to give the illusion of intelligence, always on, and memories. These are all well know (variations on RAG, markdowns, etc)

Thanks for sharing. This seems to me like a more useful approach than an agent that has full control over a computer

How does this compare to fine tuning?

It seems to me that it is broadly the same thing, except they give you the resources to do it and expert knowledge.

Interesting to see. I thought they were promoting fine tuning

Cheaper. Every month or so I visit the models used and check whether they can be replaced by the cheapest and smallest model possible for the same task. Some people do fine tuning to achieve this too.