500ms fork of a running VM with full memory state is the kind of thing I'd assume wasn't possible until I saw it work. What does failure look like — does the fork just not happen, or can you get partial state?
Launch HN: Freestyle – Sandboxes for Coding Agents
131–140 of 182 posts
Re: Launch HN: Freestyle – Sandboxes for Coding Agents
#132[flagged]
Re: Launch HN: Freestyle – Sandboxes for Coding Agents
#133I’m super interested since it seems like you have given everything a lot of thought and effort but I am not sure I understand it. When I’m thinking of sandboxes, I’m thinking of isolated execution environments. What does forking sandboxes bring me? What do your sandboxes in general bring me? Please take this in the best possible way: I’m missing a use case example that’s not abstract and/or small. What’s the end goal…
So isolation is correct. Forking a sandbox gives you multiple exact duplicates of isolated environments. When your coding agent has 10 ideas for what to do, to evaluate them correctly it needs to be able to evaluate them in isolation. If you're building a website testing agent and halfway down a website, with a form half filled out a session ongoing, etc and it realizes it wants to test 2 things in isolation, forking…
The other way might be testing VMs vs agent VMs but that would be slower as to "fork" it would need to run the test again to that point. But wouldn't need agent context.
The forking you provided adds a lot more speed.
Re: Launch HN: Freestyle – Sandboxes for Coding Agents
#134[flagged]
TBH I wouldn't recommend using it for this. I'm a big believer in agent chat running outside of the VM, where you can get much better control over the chat loop. I would treat the VM as a tool the agent is using rather than the agent's environment. Like the agent is a human using a machine and watching it, rather than trying to watch it from inside the machine. Then there are great existing observability tools, my fav is langfuse.
Re: Launch HN: Freestyle – Sandboxes for Coding Agents
#135500ms fork of a running VM with full memory state is the kind of thing I'd assume wasn't possible until I saw it work. What does failure look like — does the fork just not happen, or can you get partial state?
There is no partial state really possible. We can run out of space on a Node and just say no. But the nature of memory forking is if you don't literally do it 100% right it crashes immediately (I know cuz it took me a while too get it right).
Re: Launch HN: Freestyle – Sandboxes for Coding Agents
#136Earlier quoted context omitted.
So isolation is correct. Forking a sandbox gives you multiple exact duplicates of isolated environments. When your coding agent has 10 ideas for what to do, to evaluate them correctly it needs to be able to evaluate them in isolation. If you're building a website testing agent and halfway down a website, with a form half filled out a session ongoing, etc and it realizes it wants to test 2 things in isolation, forking…
The other way might be testing VMs vs agent VMs but that would be slower as to "fork" it would need to run the test again to that point. But wouldn't need agent context. The forking you provided adds a lot more speed.
That + its not always simple to replicate state. A QA agent in the future could run for hours to trigger an edge case that if all actions to get there were theoretically taken again it wouldn't happen.
That can happen via race conditions, edge states, external service bugs.
Re: Launch HN: Freestyle – Sandboxes for Coding Agents
#137I’m super interested since it seems like you have given everything a lot of thought and effort but I am not sure I understand it. When I’m thinking of sandboxes, I’m thinking of isolated execution environments. What does forking sandboxes bring me? What do your sandboxes in general bring me? Please take this in the best possible way: I’m missing a use case example that’s not abstract and/or small. What’s the end goal…
So isolation is correct. Forking a sandbox gives you multiple exact duplicates of isolated environments. When your coding agent has 10 ideas for what to do, to evaluate them correctly it needs to be able to evaluate them in isolation. If you're building a website testing agent and halfway down a website, with a form half filled out a session ongoing, etc and it realizes it wants to test 2 things in isolation, forking…
> and it realizes it wants to test 2 things in isolation, forking is the only way
Why would forking be the only way, when humans don't work like that? You can easily try one thing, undo, try the second thing. Your way is a faster way potentially, but also uses more compute.
Re: Launch HN: Freestyle – Sandboxes for Coding Agents
#138Earlier quoted context omitted.
So isolation is correct. Forking a sandbox gives you multiple exact duplicates of isolated environments. When your coding agent has 10 ideas for what to do, to evaluate them correctly it needs to be able to evaluate them in isolation. If you're building a website testing agent and halfway down a website, with a form half filled out a session ongoing, etc and it realizes it wants to test 2 things in isolation, forking…
> and it realizes it wants to test 2 things in isolation, forking is the only way Why would forking be the only way, when humans don't work like that? You can easily try one thing, undo, try the second thing. Your way is a faster way potentially, but also uses more compute.
This assumes you can retain the same state after an operation.
> "I wonder if this is slow because we have 100k database rows" > DELETE FROM TABLE; > "Woah its way faster now" > But was is the 100k rows or was it a specific row
Thats a great place where drilling bugs and recreating exact issues can be really problem, and testing the issues themselves can be destructive to the environment leading to the need for snapshots and fork.
Re: Launch HN: Freestyle – Sandboxes for Coding Agents
#139Earlier quoted context omitted.
> and it realizes it wants to test 2 things in isolation, forking is the only way Why would forking be the only way, when humans don't work like that? You can easily try one thing, undo, try the second thing. Your way is a faster way potentially, but also uses more compute.
This assumes you can retain the same state after an operation. > "I wonder if this is slow because we have 100k database rows" > DELETE FROM TABLE; > "Woah its way faster now" > But was is the 100k rows or was it a specific row Thats a great place where drilling bugs and recreating exact issues can be really problem, and testing the issues themselves can be destructive to the environment leading to the need for snaps…
Again, that is a problem of approach, not of compute. Compute just makes that faster, it doesn't make it possible. It's like you saying the only way to do something is with threads. It's good for some use cases, bad for others, and makes most faster, but it doesn't unlock much
Re: Launch HN: Freestyle – Sandboxes for Coding Agents
#140The observability point is real but honestly the loop detection problem is more about how you structure your agent than the sandbox. When I've had agents go rogue, the issue was always the outer loop logic, not visibility into the VM. What does your current loop controller look like?