Relative to other results I agree. But on an absolute measure, there is not a single element in the current bicycle that is real-world accurate and many elements are omitted or non-physical (eg, the transparent seat tube top, entire lack of a head tube).

Consider a series of followup benchmarks.

With a fresh context of the LLM under test, ask it to generate a list of findings for how the pelican-on-a-bicycle SVG that was produced is inaccurate compared what the real world scene might appear, accepting for the limitations of SVG as a medium. Then, feed back the list of findings to the original context for a second try. The benchmark can stop here by humans looking at the result and forming their own conclusion.

Next phase is to repeat the analysis phase using the 2nd context to determine what findings were satisfied and what new inaccuracies are found. These two differences can form a second benchmark.

Last phase is to iterate with the goal to drive the number of findings to zero.

I wrap bubblewrap in a script that supports config files to allow different "profiles" of use (analogous to eg firefox profiles). The bwrap starts with the whole filesystem mounted read-only, then mounts the current directory read-write and then applies further bind mounts for devices, special case other read-write (eg, ~/.cache/) and to mount empties to cover sensitive directories (eg, ~/.ssh/). The profile also specifies the default command to run and for claude, it gets yolo mode.

I thought maybe NERSC doesn't accept jobs from private corporations but I checked and that's not true, as long as results are not held proprietary.

Perhaps ANL was used as they have a lot of compute and they lead and host the Genesis Open Models Initiative?

From your link, 2048 B300 GPUs were used for 6 months. If google search is right, NERSC has 7168 A100. B300's are way more capable than A100. To do this training in 6 months, "3 NERSCs" would be needed.

Between the political angle and the technical, I'd guess these two make up a big chunk of the answer.

US national lab scientists are not even civil servants. The labs themselves are run by a corporation under contract to the DOE and the scientists work for that corp. The managing corporation changes from time to time and the scientists transparently start working for whatever assumes the replacement. The land, the hardware, the buildings and any physical products are owned by the US gov't. To a very large extent, the intellectual output is set free to the world in the form of papers, presentations and to some small extent (eg compared to CERN) in the form of software.

I find this depends on the LLMs being used and the person using them and the problems being solved.

Like, Fable can be sent off to do some big thing for a long while and I find myself getting bored and move over to push on some other thing. Or, while reading a paper I have a string of follow up questions and ideas and launch them via web or CLI agent. Or I bounce between multiple chores in different packages, each of which is fast for an LLM and a low cognitive burden for me. Then other times, something needs my full, ongoing and serial attention where the LLM turn is only a minor element. I'll use the brief LLM interludes to get up, walk around a bit, stretch and think.

As for Herdr, it seems nice when I tried it a few weeks ago. But, I'm surprised it is getting so much attention (kudos). Like many people, I've developed more than one work-alike before Herdr hit the scene. They were based on tmux which I have concluded I simply detest. In the end, I made a little agent hook script that speaks to Kitty terminal and that plus Kitty and a stable SSH persistent connection gives 80% of what I was looking for. I do still like the "control panel" aspect of my past and herdr's tries. Adding that would get me another 10%.

:)

The OP is not sitting in a one-way flow of info:

    LLM->human->code 

    LLM<-->human<-->code.  

I'd argue that anytime we drive an LLM through more than one turn (and/or more than one session) we are really doing a human-is-the-loop thing. The OP's extreme case of begin the only thing editing code is on a spectrum with the other extreme being vibe coding (never looking at output code, but still interacting with that output in some way).

Off the spectrum is what I call LLM-vomit. A human one-shots something and puts it out for others to see, suffer and clean up or ignore. This is code that is encountered literally out of context and can only be further improved (if that is even attempted) by approaching it from first principles. Such code is akin to people using LLM to generate an answer delivered to another human. Both flavors (sorry) of LLM-vomit are bad. I can prompt my own LLM to do that, don't do it for me.

That said, if these strings are really sensitive and I'm too lazy (or not trusting the human user) to self-censor, I'd not rely on this particular kind of tool for censoring. I'd use local LLMs or cloud LLMs where privacy is part of the contract.

Define a subgraph of atomic nodes as itself a node with its ports formed from as-yet unconnected ports of its atomic constituents. Compose yet higher subgraphs of subgraphs and atomic nodes. Package all this in some way.

This is directly analogous to syntactic programming where functions aggregate other function calls and all that packaged into a library with an API.

- After an incorrect key, require two (or more) consecutive valid key entries.

- After an incorrect key, no longer accept that nominal key until a secondary key is supplied.

    Your search - site:claude.ai/share - did not match any documents.

Two approaches:

You can pin the version of `ruff` in `pyproject.toml`.

You, to let ruff command version advance but pin the settings to a prior version:

    uvx ruff@0.15.22 check --isolated --show-settings | flat2toml > pinned.toml
    

    extend = "pinned.toml"

What's really tiring is reading such facile "critiques", especially when they are not even applicable.

And, the whole idea of copy/paste having to use both mouse AND keyboard (select Ctrl-c click Ctrl-v) is barbaric. X11 got it right and it seems all "modern" apps are trying really hard to introduce barbarisms.

Hmm, pandoc? Surely....

    M-x org-import-