jj with agentic coding is really underrated. The automatic committing is awesome for being able to see diffs between every prompt, roll back changes done by a given prompt, etc.
Notably the posted project is Apache licensed, and your project is Elastic licensed. Your project looks cool and you've clearly put a lot of thought into making it useful, but the license makes it a non-starter for me.
It's not that they didn't care, it's that they did care in the wrong way. A non-replacable battery means people will be more likely to buy a whole new device if (when) the battery fails.
What does "AGI" mean to you such that we have not had it for years already? Whenever I see people mention AGI it's in the future tense, as if we don't have artificial machines that can apply intelligence to general domains.
"Very often" sounds like a lot more than I would say. I've been using Qwen 3.6 27b Q4 in Pi (with out any anti-looping extension) daily for weeks now, and I've had it get stuck in an infinite loop maybe 3 or 4 times.
The most promising alternative is making it legal to build housing near where people want to be (commercial districts) and make it legal to build places people want to be near where they live (build cafes, shops, etc in suburbia). Any help that AI could have on the situation would just as easily be applied to working from home without AI.
> This is "whatabboutism" which is a logical fallacy.
No it isn't. You don't optimize a piece of software by profiling it and rendering a flame graph, and then ignoring the sections of code that the most time is being spent in. You work on optimizing the paths where the most time is being spent, because that is where your effort has the most room for impact. If we are trying to optimize carbon emissions instead of time, we look at the biggest sources of emissions first, because that's where our effort has the most room for impact.
> Someone doesn't have to talk about the climate impacts of cars every time they talk about the climate impacts of AI.
I never said they did. I said they should be fighting both if they actually care about the issue.
> Peruse my personal blog and you will see that I, in fact, ran a whole city council campaign on a platform of "to fight climate change we should not be driving".
Excellent, you are fighting both because you care about the issue. Thank you for your service.
It's important to emphasize that cars are the leading source of carbon emissions. Anyone fighting against AI on the basis of climate change should be fighting for safe and reliable alternatives to driving everywhere.
I read it as "Google is indifferent to me" rather than "Google specifically dislikes me", as a point of clarification that they didn't get access by being personally selected.
> To an untrained eye, it seems like go, but with manual allocation.
I've written a decent amount of Zig, Go, and C, and I often describe Zig as in between Go and C. So your untrained eye seems pretty accurate. Maybe it's just not the tool you need, and that's fine! I could get excited about a new tractor that is well built and leans heavily into right to repair activism, but I live in a city and wouldn't use it.
Can you link the model? I also have a 24gb card (7900 XTX). I've been having success with the dense 27b model, but I'd like to see if the 35b iq4 is any better.
I have been using pi (and previously the codex cli) with Qwen 3.6 27b with 100k context for my development at work, and I have been very blown away by how well it works. It's not perfect, but it's enough to accelerate my normal development flow. I mostly use it for writing Go and C#.
email: contact at robbyzambito.me
bksy: @zambyte.robbyzambito.me
zambyte.at.hn