Even if you don't like Electron, I was able to get Claude to build Electrobun and Tauri apps as well. I don't understand what benefit Glaze will bring outside of more lock-in?
They will come for medical advice provided by AI as well. Doctors have been gate keeping that forever and they want you to have to go thru them instead of diagnosing yourself thru AI.
Yes, there are people that will misdiagnose themselves, but I’ve read stories where doctors ignore patients symptoms or wave them off, and ChatGPT helps them find the underlying issue and actually improve their lives. Even if doctors and the medical field can’t handicap AI giving medical advice, I’m sure they are going to make it much harder for patients to get their hands on their own scans and bloodwork.
I know because I've lived it. My other comment on this post:
> I have narcolepsy. It took a dozen or so doctors and years of suffering before I got a correct diagnosis, and even then it was only because I diagnosed myself with Google and then specifically made an appointment with a doctor who specializes in it. Gemini nails it when I put in my symptoms.
Also, I had to vouch for your totally legit comment b/c somebody who doesn't want other people to read it flagged it dead.
as someone who was failed by psychiatry and tried all regular medications AI helped me find an off label treatment for my mood disorder that has had a profoundly life changing experience for me. what they’ll be doing is removing experiences and stories like this where gaps in knowledge allowed psychiatry to fail and AI helped me the find the cutting edge of research to get the treatment i needed desperately!
Extend that to marketplaces too, all their search UIs have dark patterns forcing you to see their “recommendations” instead of being able to manipulate the results like you want.
They were banning people and those people couldn’t even cancel their subscription. That’s a rookie mistake and you expect the same company to have a flawless ban system?
I haven't used them all but based on my partial research so far:
- OpenClaw: the big one, but extremely messy codebase and deployment
- NanoClaw: simple, main selling point is that agents spawn their own containers. Personally I don't see why that's preferable to just running the whole thing in a container for single-user purposes
- IronClaw: focused on security (tools run in a WASM sandbox, some defenses against prompt injection but idk if they're any good)
- PicoClaw: targets low-end machines/Raspberry Pis
- ZeroClaw: Claw But In Rust
- NanoBot: ~4k lines of Python, easy to understand and modify. This is the one I landed on and have been using Claude to tweak as needed for myself
IronClaw’s security architecture sounds plausible, but I have not audited it. Plugins can only access remote endpoints you’ve specifically allowed it for. Secrets aren’t available to the LLM - they are injected where the LLM requires it but only secrets authorized for that plugin are available to it. Together those two things provide an answer to a huge range of the most common prompt injection vulnerabilities, such as credential extraction. So you can give it access to your bank account and email and it can’t email your bank password to an attacker. But it could still transfer money to them.
The only secure way to use any of these tools is to give them very limited access - if they need a credit card give them a virtual card with a low limit, or even its own bank account. They can send email but only from their own account; like a human personal assistant. But of course this requires careful thought and adds friction to every new task, so people won’t be doing it.
Nanobot's was not great (cron + a HEARTBEAT.md meant two ways to do things, which would confuse the AI). But because the implementation is so simple, I could improve it in a few minutes in my own fork!
I'm only using NanoClaw, but I like that I could (and did) just review the code it has, and that it uses containers for each agent (so I can have different WhatsApp groups working on different things and they can't interfere with each other), and that I could (and did) just swap those containers out easily for guix shell containers.
I am pretty confident that I know how the agent containerization works. In general there's really not a lot of complexity there at all.
If one wants, one can just (ask Claude to) add whatever functionality, or (and that's what I did) just use Claude skills (without adapting NanoClaw any further) and be done with.
What is annoying is that their policy is instead of integrating extra functionality upstream, they prefer you to keep it for yourself. That means I have to either not update from upstream or I am the king of the (useless so far--just rearranging the deck chairs) merge conflicts every single time. So one of the main reasons for contributing to upstream is gone and you keep having to re-integrate stuff into your fork.
General advice would be to mark the email as spam or junk and hopefully their email platform penalizes them, but this has been working less and less. Email has truly become pay to play now.
Looks interesting but also, they are saving everything to a database. It's not simply an alternative frontend for Github akin Nitter or NewPipe (for Twitter and TY respectively).
I was using Antigravity the proper way, but why would I risk my account using this subpar software? OpenClaw and Opencode literally obfuscate the API call exactly like Antigravity calls it. Do you really trust Google to only catch misuse using this dragnet?
I can guarantee in their attempt to stop OpenClaw users, some users using it normally will get caught in the dragnet. It could mean your whole Google account is suspended, not just for Antigravity.
I would highly encourage you to not only stop using Antigravity oAuth for OpenClaw, but to use Antigravity with a side account or stop using it altogether. Is using Antigravity worth losing your main account or getting it banned for using paid services (for extra storage, YouTube premium, etc). Even side accounts are risky since in the post thread people are saying Google applied the ban to all their accounts.
reply