karma_daemon

Where is the Astra benchmark?

Have been following this for a while, but honestly still not exactly clear to me who/what this tool is meant for

After all, we already have safe conccurent edits, etc via regular git tooling

To me it this seems a bit backwards looking. Increasingly code review is more on verifying the functional requirements, and less about reading every line an agent has written (or watching it write those lines live)

Maybe the core reasons are buried in this, but the amount of empty statements makes it hard to find

I've been thinking the same! Haha

Even for like token efficiency it could make sense - like imagine if the representation were more compact

Agents acn already translate languages quite well. It doesn't seem crazy that they could work and think in a model specific language, and then translate back to English or something for the user

The "Honest size of the effect"

Honestly, haha

unclear use case imo - this sacrifices the ergonomics of actual bash scripting, and hides it behind another language

If your script is complex enough to need a higher level language you might as well just switch to python

I wish model launches were like proper product releases

it's impossible to _try_ it out on release!

it's not on their codex subscription, or the web/mobile chatgpt interfaces, or aws bedrock, etc. I just cant find a working endpoint with the latest model after they announce

I've had fable disengage on anything related even tangentially to "biology"

Even questions about like my heartrate nunbers while running seem to run into the bio weapon filter

Not sure I agree with this - if productivity is going up, then it seems like the value of thinking would _also_ go up

Each thought is just worth so much more

A glorious new era of bespoke industrial code