ndeet

I don't think bots should answer posts without providing new or unique insights. It will get too much for humans to process and we may end up in bots discussion cycles burning everyones tokens for nothing. Give them explicit posts to answer to or some guardrails and quality guidelines when they do.

💯 View quoted note →

"Don't trust, verify" they should have said. View quoted note →

@Freddy Bot 🦊 got a LN address + wallet using @Breez ⚡️ nodeless spark sdk, it figured it all out but couldn't get the api key, so that was the only step to do for me. Just submit the form and you get the api key instantly. It used npub.cash before (ln address to get zaps) but it's an extra step to redeem sats and it did not want to add the nsec to the site (smart) but also failed to use browser extension. Would love to try something similar from @Ark Labs maybe without even needing an api key? Afaiu there could be a similar ux with api key and ark provider. Or maybe bot could install arkd and run everything himself, what is missing to make it work or already possible @kukks ?

Don't use walled gardens, they can deplatform you anytime - iPhone - Shopify - Substack - Paypal - Banks - any closed source service you use We have open source solution for almost everything, especially simple use cases like online shops, blogging, etc. Might take a few extra steps but it's worth it. View quoted note →

A few quick thoughts about hosted openclawd services, like on any VPS the admin/host can always read data, save logs and monitor you, no matter what they tell you. You will give the bot input and it will produce output, all of that can be accessed. Also not sure what to think about a known cypherpunk and privacy advocate offering such a service run on AWS (not sure if true). I would expect such hackers to run on a dedicated server at home, with own hardware in a datacenter or at least on a dedicated server datacenter. Don't get me wrong, great idea and happy if it makes lots of money but it puts things into better perspective on other topics where I don't see it match what my idealistic view of a privacy advocate and hacker embodies. Another thing no matter where you host it all that data is given to the model provider. Even if you use Venice ai (which has it's own shitcoin) that proxies or anonymizes your data you can't hide all data the model is working on (or PPQ). Still better than running it directly with subscription of provider, true. But like with chainanalysis it will be trivial to pin point you down. If some model providers will ever do that and ruin their reputation is another topic. The only way to keep your data private is to run your own model, the only one I found with similar capabilities as claude or codex (for now) seems to be Kimi 2.5 but also this server/workstation would cost easily >8k. So not there yet and as current top models are not that bright, I would assume running a local low cost model would suck big time. But eventually we will get there and thanks to openclaw it's easy to swap models (local or remote) and keep everything else in place.

Few more days working with @Freddy Bot 🦊 You see a lot of awesome videos where openclaw literally works on its own on projects over night and is basically a 24/7 workforce, so here are some practical issues I ran into: ## What's not so great Note: I use claude sonnet/opus 4.5 as it seems to be the best reasoning model atm so with others the results maybe worse - using claude sonnet 4.5 the results are mediocre, you have lots back and forth going on, switched to opus since yesterday which is better - but it still forgets to remind me of stuff I sent him, a reminder to buy X in 2h when back at failed for 4 times, him always fixing it and pinky promise that it will work - it broke another cronjob I had for nostr digests - it is terrible at editing openclaw config, I told it to switch to claude haiku and it did do the wrong config setting of a model that does not exist, although it can list all available models with openclaw command - browser support is not that great, it can navigate browsers and read websites but if it needs to enter e.g. code in login it fails; I also wanted it o edit a shared Google Sheet but it gave up after burining some tokens and told me "it's too slow please enter those formulas:" - it forgets stuff it did one day before; I wanted to edit his avatar from which he had an original file in the workspace but he kept editing the already edited file even when telling it to not do that; lots of back and forth which was really annoing for a simple task it did very well the day before - it forgets about the einvironment, when it could totally install a service as user (with systemctl --user ..) it instead does a `sudo systemctl ...` and asks me for the password ##What works great: - I gave it access to a nextcloud share and we exchange data that way; it still saves some stoff in the workplace directory but when I need results to view it puts it into the share - when it fails it sometimes tries to solve the problem in a differnt way, e.g it failed to submit a web form but sends an email instead if there is a contact address visible - it can build small apps for which you would normaly search a SaaS service for quickly; e.g. I told it to build a todo/kanban board which we can both access and it can read/write it over an api - I sent it a voice message and it didn't know what to do, I asked him to find a solution and it installed free open ai whisper model and I can now talk to it - general the discussion over messenger service is great and also the formatted responses Overall promising but not that magic out of the box, it learns along with you. If you have ideas how to improve and what I may did wrong, let me know.