woodylondon
Joined 14 years ago
Joined 14 years ago
Are you planning an API? Would love to spin up a version for Apple TV.
So my understanding of the differences between chat, code and co-work; but may well be wrong!
Chat is the human, talking directly to the LLM - old school. Very basic can create docs etc - but saves in a temp folder. No real access to your local PC.
Cowork / work - Human talking to an agent, which can then use tools to do work. Also runs in a container, allowing it access to your drives/computer.
Claude Code / Codex - No longer in a container, full access to the computer, depending on what permissions you give. No longer locked in a container. + The agent is more focused on coding than cowork / work.
You might need to queue for a little while on a weekend or at prime lunchtime.
The others you need to book weeks ahead, so agree with the previous post that they do make it hard. Sky Garden is not one of them.
The problem is that once you're on the paid plan, you're exposed to unlimited risk if your worker goes crazy due to a stupid code bug or if you're hacked. As a solo dev, it's a risk I simply cannot take; I could wake to a bankruptcy bill from Cloudflare. Even as a company, an employee could sign you up and your accounts team would have no idea of the risk.
I am using Supabase at the moment, and see they have a hard cap now. and so does Vercel after they had some nightmare stories of large bills in the past.
I am not sure why / what CloudFlare think about this - or simply dont care.
Actually, rebuilding WordPress without the ecosystem is kind of the point. For example, would Divi or the major page builders rebuild their entire products to support this? I doubt it
Anyone installing this on their local machine is a little crazy :). I have it running in Docker on a small VPS, all locked down.
However, it does not address prompt injection.
I can see how tools like Dropbox, restricted GitHub access, etc., could all be used to back up data in case something goes wrong.
It's Gmail and Calendar that get me - the ONLY thing I can think of is creating a second @gmail.com that all your primary email goes to, and then sharing that Gmail with your OpenClaw. If all your email is that account and not your main one, then when it responds, it will come from a random @gmail. It's also a pain to find a way to move ALL old emails over to that Gmail for all the old stuff.
I think we need an OpenClaw security tips-and-tricks site where all this advice is collected in one place to help people protect themselves. Also would be good to get examples of real use cases that people are using it for.
This is both a technical and an educational problem that needs to be solved. The technology for network monitoring needs to be easier for parents to install, with all 18+ content blocked by default, etc. Companies have software installed that tracks everything you do—every piece of software you install (or can't install if the system is locked down). We need this level of technology available at home.
Now, if Microsoft, Google, etc all got together, backed by the government, they could build this in months, and so the cost would be low and shared.
All mobile phone contracts block access to 18+ content. If a child has a mobile phone, then yes, block access to social networks.
It could be a plug-in device that connects between your router OR an ISP-level feature that, when you first join, asks whether there are children in the house. If you say no and there are, then that's breaking the law.
When you first install it, a well-designed interface would prompt you to select your children's ages and add their devices (laptops, iPads, etc.). You install the client software locally, link everything up, and the whole system tracks and monitors usage. Problem solved.
If children go to friends' houses, there should be a way for them to join as guests so parents can still see everything.
If children go to grandparents' houses or friends of friends, then either you need to install this box to manage access, or there's no Wi-Fi. They'd have to use their mobile data.
What I don't agree with is that childless people have to comply. I don't know any children, and all the ones I did have have grown up now. Fundamentally, I do think that we need to find a better way to stop social media bullying, the fact that beheading or gore videos are so easily accessible - I think that's worse than any "normal" porn!
Children cannot drink or smoke. It's not like you can argue against this; parents have a responsibility to stop that from happening. It's no different; in fact, it's worse.
Now, of course, once kids get to 14+, they will find a way. Since the start of history, we've all gone through that, and nothing any government does is going to stop children from pushing boundaries, learning, and experimenting.
My concern is that Gov will go down a route where every website you sign up to requires AgeID. It will be impossible to have Anon accounts anywhere. Sites will love it as more advertising and tracking for everyone. I stopped posting on social networks, as the second you say anything slightly different from someone else, the trolls come out and attack. I simply could not be bothered, and so deleted all social networks.
Waiting now for the HN trolls to attack - don't worry, I simply cannot be bothered to respond :)
I also think they tend to be the older ones among us who have seen what happens when it all goes wrong, and the stack comes tumbling down, and so want to make sure you don't end up in that position again. Covers all areas of IT from Cyber, DR, not just software.
When I have moved between places, I always try to ensure we have a clear set of guidelines in my initial 90-day plan, but it all comes back to the team.
It's been 50/50: some teams are desperate for any change, and others will do everything possible to destroy what you're trying to do. Or you have a leader above who has no idea and goes with the quickest/cheapest option.
The trick is to work this out VERY quickly!
However, when it does go really wrong, I assume most have followed the UK Post Office saga in the UK around the software bug(s) that sent people to prison, suicides, etc. https://en.wikipedia.org/wiki/British_Post_Office_scandal
I am pretty sure there would have been a small group (or at least one) of tech people in there who knew all of this and tried to get it fixed, but were blocked at every level. No idea - but suspect.
cannot login to get to workers to check - auth errors
I thought this was the point of a cached CDN!
I have managed tech start-ups around the world and now work in digital transformation and tech consultancy. I started working in tech back in 1992 with DOS, Clipper, Visual Basic, and Delphi, then moved into the first .COM boom, followed by mobile technologies.
I skipped the crypto and web3 boom, but I believe AI is the new internet, and it feels like 1999 all over again!