I've had good experiences with the Mistral Voxtral models (I've used the API, but some of the model-variants are open weight)

Idk, it almost seem a workaround for slow/broken go-back? If go-back is fast and state preserving, it's basically a fullscreen modal.

All(?) browser open links in a new tab when middle-clicked?

Can you please fix https://github.com/anthropics/claude-code/issues/43713 ?

Wish reword took a commit range though

I had to check and `jj describe` does. You get all the commit messages in a single file to edit, with headers separating them.

I don't want "standby", I want suspend where the only power usage is keeping the ram alive...

git bisect --first-parent

So this means I can not resume a session older than 30 days properly?

I have no idea; you have to check their docs.

AFAIK what they do is that they calculate a hash of the true thinking trace, save it into a database, and only send those hashes back to you (try to man-in-the-middle Claude Code and you'll see those hashes). So then when you send then back your session's history you include those hashes, they look them up in their database, replace them with the real thinking trace, and hand that off to the LLM to continue generation. (All SOTA LLMs nowadays retain reasoning content from previous turns, including Claude.)

I see. If that's just hashes and not encrypted content I can't see how they can resume old sessions properly. IIRC they have a 30 days retention policy and surely the thinking traces must be considered data. Wonder how this works with the zero-retention enterprise plans...

So we are paying the price for the cost of infra need to protect their asset which was trained on data derived from the work of others while ignoring the same principle? I need this to make sense.

> I wonder if there is a more general solution that can make models spend more compute on making important choices, while making generation of the "obvious" tokens cheaper and faster.

I think speculative decoding count as a (perhaps crude) way implementing this?

Source of that image though.. ?

An AI prompt in June 2025.