The difference is never before has the presentation of a computer and its capabilities made the person on the other end decide "Wow, this is like talking to a real person. I'm gonna date this computer"
We as a society should weight the cost/benefits of new technologies like this. What is the actual benefit of gigantic AI data centers? Is that worth the costs of the data centers to the power grid
Not necessarily, C#'s incremental source generators mean you could simply slap an attribute onto a class you want to use the non-boxing pattern with, and it'll just generate the pattern for you.
Yeah I also don't really write commit messages. If your pull request becomes associated with that commit, and the history gets squashed, then that one commit becomes a link to the pull request where all the necessary info is. I just write "commit" for all my messages.
On my local copy of the repo, commits are notes to myself. I don't use the `--message` switch. I let git bring up my $EDITOR where I type what I did since the last commit. This helps when I'm writing the PR description and when I'm rebasing the branch on top of the main trunk. And then some time, I need to do a bit of git-fu and split the changes into different PRs. Hard to do this with generic messages.
But I use magit and I can commit specific lines and hunks as easily as files. That helps with managing changes to meaningfully group them.
Agreed, the thing I'd be most interested in is the isolated execution environment you mentioned. Agents running autopilot are powerful. Agents running unsupervised on a machine with developer permissions and certificates where anything could influence the agent to act on an attacker's behalf is terrifying
I recommend running the agent harness outside of the computer. The mental model I like to use is the computer is a tool the agent is using, and anything in the computer is untrusted.
Kind of. The chat logs of the agent are trustworthly, as should any telemetry you have on it or coming out of the VM. Its behavior should be treated as probabilistic and therefore untrustworthly.
It’s untrustworthy because its context can be poisoned and then the agent is capable of harm to the extent of whatever the “computer” you give it is capable of.
The mitigation is to keep what it can do to “just the things I want it to do” (e.g. branch protection and the like, whitelisted domains/paths). And to keep all the credentials off its box and inject them inline as needed via a proxy/gateway.
I mean, that’s already something you can do for humans also.
I would recommend not giving an agent the full run of any computing environment. Do handle fine grained internet access controls and credential injection like OpenShell does?
I used to believe this, but I think the next generation of agents is much more autonomous and just needs a computer.
The work of a developer is open ended, so we use a computer for it. We don't try to box developers into small granular screwdrivers for each small thing.
Thats whats coming to all agents, they might want to run some analysis with python, want to generate a website/document in typescript, and might want to store data in markdown files or in MongoDB. I expect them to get much more autonomous and with that to end up just needing computers like us.
The difference is that I am not always legally liable for what a rogue developer does with their computer - if I had no knowledge of what they were up to and had clear policies they violated then I'm probably fine. But I'm definitely always liable for anything an agent I created does with the computer I gave it.
And while they are getting better I see them doing some spectacularly stupid shit sometimes that just about no person would ever do. If you tell an agent to do something and it can't do what it thinks you want in the most straightforward way, there is really no way to put a limit on what it might try to do to fulfill its understanding of its assignment.
That is not the same situation. Writing is a thing we do to communicate with other people, and to engage our own thinking. It's creative, it's exploratory, and it's a human-to-human practice. It is a top-level abstraction. The only higher you could possibly go is beaming your thoughts directly into someone else's brain.
Also it irks me to compare writing to a calculator's log function or a self-driving car. There are absolute correct/perfect outcomes in those situations (the log function produces the correct number, the car drives you to your destination without injury or unnecessary danger). That is not the same for most things AI is attempting to be used for.
Creating graphic arts is also a form of communication. But Procreate makes it easier, even for novice to create amazing art. Consider an aircraft, the pilot is given just few knobs to fly the plane but it still takes you from one location to another. The aircraft is indeed very complex than the knobs given but we can hide most of that complexity underneath the knobs assuming happy path flights most of the time. The higher abstraction I am talking about is the future jargons themselves. AI will allow us to create far more complex stories. Imagine one complex jargon represented by a mandelbrot fractal (to paint a picture of the complexity involved), another represented by burning ship fractal. What kind of operations can I do with these two complex ideas. Can I explore a complex conceptual space with it? We would just say to the AI, subtract one fractal from another and it would handle the details (the definitons, references, related ideas in a free form manner). This is exploration itself. Procreate gives you brushes. AI gives you something similar in conceptual space.
reply