MaxMatti

I've used the zai subscription, opencode go und cline-pass in the last few months and would recommend the latter. Zai quickly drains your quota as soon as the context window is at more than 10-20% and opencode was a bit unreliable at times.

If the goal is just destruction then letting it free in random public places is not that hard. Especially in countries where wearing a mask is not frowned upon.

How does it save tokens?

I've heard lots of people use it to actually find out what you were being banned for even when the company absolutely does not want to disclose it.

Or maybe it's just lazy programmers, wouldn't be the first time.

I'd like to see them try to increase prices as long as open source models that are roughly in the same league are available

I have yet to find a messenger with a better UX than Telegram. And I have tried lots in countless attempts to get away from this badly encrypted russian App.

Theoretically yes, but in reality I have found that often it's much easier to just fix something locally or with a workaround rather than jumping through all hoops required to get somebody in another team or even another company to understand and agree with you on your (or your teams) issues, let alone fix them in a satisfactory way.

When I downloaded it via F-Droid earlier today it did what wanted. Unfortunately Android Auto is only enabled in the Play Store Version, so I downloaded that and there it went the same as for you. At least it immediately prompted me to download my local tile set when I tapped the geolocation button to zoom in.

I still feel that during agentic workload sometimes it would be nice to have the model identify it is veering off the main track, send out a "keep the cached states and tell me which they are" command to the inference server, do the side thing (such as handling an error that plopped up that has not that much to do with the main task) and return back to the cached state with just a comment tacked at the end to say "oh and btw I fixed DNS" instead of having the DNS debugging inside the context window now. Maybe other harnesses just steer the models more towards using subagents for such tasks and my pi is misconfigured. I can use the tree feature, but having insight into what's cached would be nice there.

How's the battery holding up during vibe coding sessions or occasional LLM usage? I've been thinking about getting a MacBook or a laptop with a similar Ryzen chip specifically for that reason.

The paper does mention that you can have your ssh keys signed by a ca, so in a company the it staff could configure everybodys os to only trust ssh keys signed by the organization.

There's conflicting information in the readme about whether --best-effort is enabled or disabled by default.

I'm unsure how much of a difference that really makes as there's lots of distractions in my (and probably most peoples) morning routine that are not related to my phone. Boring things like the hygiene routine but also things that come up and require thought such as (almost) empty grocery items or things related to the commute such as radio in the car or ads in public transit. While most of these are not specifically engineered to be attention seeking, I still see most of them as distracting and my focus only starts when I sit down to do some work.

Above a certain size all communities sooner or later turn into cults, most of the time around one or a few persons. The ones that you don't perceive as such you just haven't looked into close enough. I wish it were different but so far I have yet to find a community that doesn't fit that description. Not just open source, not just software, any community.