John McPhee talks about a similar model for the Mississippi River in “The Control of Nature” Well worth a read. Fun stories about Hawaii and Los Angeles too, iirc.
Gell-Mann suggests I should treat the rest of your post with skepticism.
EDIT: maybe you meant the UK total primary energy? I feel like that's extending the boundary a bit far. Should we start digging for uranium? Or stick to renewables, but only with locally sourced silica and rare earths?
I made a CLI (+skill) so agents could edit files with verbs like `insert A1:A3 '[1,2,3]'`, but did some evals and found it underperformed Anthropic's approach (just write Python).
I deliberately didn't mention this because I think most of the pain with Github over the last year is probably caused to some degree by their scale, which seems like an unrelated issue. (But maybe not.)
If anyone from Astral sees this: at this level of effort, how do you deal with the enormous dependence on Github itself? You maintain social connections with upstream, and with PyPA... what if Github is compromised/buggy and changes the effect of some setting you depend on?
I’m surprised it works for you with such a simple config? I’m the one that added the allowRead option to Claude’s underlying sandbox [0] and had quite a job getting my toolchains and skills to work with it [1].
[0] Fun to see the confusing docs I wrote show up more or less verbatim on Claude’s docs.
Interesting, that's not been my experience! Maybe you've got the list of things to allow/block just right. While testing different policies I've frequently seen Opus 4.6 go absolutely nuts trying to get past a block, unless I made it more clear what was happening.
Yeah I think for general use the transparency of what your thing does is really great compared to a pile of TypeScript and whatnot.
How do agents tend to deal with getting blocked? Messing around with sandboxes, I've quite even seen them get blocked, assume something is wrong, and go _crazy_ trying to get around the block, never stopping to ask for user input. It might be good to add to the error message: "This is deliberate, don't try to get around it."
For those using pi, I've built something similar[1] that works on macOS+Linux, using sandbox-exec/bubblewrap. Only benefit over OP is that there's some UX for temporarilily/permanently bypassing blocks.
There is sandbox-runtime [1] from Anthropic that uses bubblewrap to sandbox on Linux (and works the same as OP on macOS). You can look at the code to see how it uses it. Anthropic's tool only support read blacklist, not a whitelist, so I forked it yesterday to support that [2].
How does this work with self-hosting? Is the assumption that self-hosters won’t run into this problem?
For most use-cases I’d probably prefer to just delete the payloads some time after the job completes (persisting that data is business logic problem). And keep the benefits of “just use Postgres”, which you guys seem to have outgrown.
I got pi to write me a very basic sandbox based on an example from the pi github. Added hooks for read/write/edit/bash, some prompts to temp/perm override. Have a look, copy-paste what you like.
The people pushing oh-my-pi seem to have missed the point of pi... Downloading 200k+ lines of additional code seems completely against the philosophy of building up your harness, letting your agent self-improve, relying on code that you control.
If you want bags of features, rather clone oh-my-pi somewhere, and get your agent to bring in bits of it a time, checking, reviewing, customising as you go.
This is super interesting framing. I’m definitely a completer, not that I like much about Slack. Probably useful to have this kind of discussion before/while making knowledge management decisions in startups.
I don't know enough about the science side to take it any further on my own.
The "tech" part of what I started building is really quite simple: convert the images to Cloud-optimised GeoTIFF, then do range requests to S3 from the browser.
Might not be possible to find any, they’re expensive and niche. If you reach out (email in profile) I can show/share how it works (nothing currently public).
I did something similar once for a mining technique called “core logging”. It’s a single photo about 1000 pixels wide and several million “deep”: what the earth looks like for a few km down.
Existing solutions are all complicated and clunky, I put something together with S3 and bastardised CoGeoTIFF, instant view of any part of the image.