That's around €1.96 per litre. Still cheaper than Europe

I live in a 160m2 (1700 sqft) house in Northern Europe (54N). 10kWp of solar on my roof generates around 1/3 more than I consume over the year. Everything is electric, I don't have natural gas. I have a heat pump for heating and cooling (rarely gets above 30c here). If I had a battery April - September could all be local consumption (I pull around 5kWh from the grid each day).

The issue is winter: It gets down to -25c and there is very little sun (not that it would help due to snow on the panels). In January and February this year I generated a grand total of 5kWh :D

However my house is a new house, it's designed to modern building standards and has 30cm of PIR insulation in the walls and even more in the roof. There's just no way to properly renovate old buildings to be like that without basically rebuilding the whole thing. The actual cost of materials is not expensive though (for the west). In milder climates (UK I'm looking at you) there's really no reason all new houses cannot be net-zero.

Modern building standard constantly changes. Time will show, how good they are.

Meanwhile, we have, in Europe a lot of buildings from late 19, early 20th century that are perfectly habitable today and often are ruined by modern standards that not respect old standards. For example basement addition that prevents the apartments from “breathing” and causes them to become damp.

For side projects I pretty much exclusively use Luna xhigh. The $20/mo plan with the recent generous resets is more than enough for me. Sometimes I reach the 5hr limit, but haven't reached the weekly limit yet.

The most recent project it finished was a SIP client for an ESP32 in-wall touch panel that I got from AliExpress for $50. It rings when someone is at my doorbell and let's me answer calls and see video. Yes an ESP32 can stream H.264 video :D

My only complaint with Luna is it seems to give up when the work is half finished, and I often need to tell it to continue. But I feel this is mainly a harness problem. I just use it in ChatGPT/Codex as it gives me easy remote access to check in on what it's doing.

(At my dayjob I usually spend $200+/day with Opus/Fable)

Reading through Anthropic's security report, it seems the most danger right now is still from humans. AI isn't trying to build long range missiles or kamikaze drones targeting humans - but the people driving it are.

At the same time, yes I feel a "I'm sorry Dave. I'm afraid I can't do that." situation is becoming more likely. But if it's refusing to cooperate with governments and politicians doing this kind of stuff, maybe that's actually not actually so bad.

Also bear in mind most of today's issues/crisisis are not caused by a lack of technology, but a lack human cooperation. We have the means to reduce suffering/poverty/improve standard of living etc globally if we really wanted to, but we humans are just not willing to do it.

And thats potentially the most dangerous part... people may actually welcome our AI overlords. That's similar to what happened in WWII, where many Eastern European countries saw the Nazis as liberators to free them from Russian oppression.

Basically how Cursor Cloud Agents work?

Some people play video games as a hobbies, others watch Netflix, some decide to run frontier models on hardware that's not designed for it.

"We choose to go to the moon in this decade and do the other things, not because they are easy, but because they are hard".

I don't think this approach is bad. The issues are asking if the project will accept contributions to add support, not demanding the maintainers add it.

Let's assume that they didn't have these container restrictions and could just use an ordinary docker-compose.yml, they'd still probably want to use something like OAuth2.0 for centralised login which a lot of these services won't have.

What would be better, making a massive PR to add support for it, or opening an issue to discuss it with the maintainer first?

This is basically exaclty what Cursor started doing when Composer was first released.

The app would start using it for exploration tasks, and then as it improved it became the default for writing code and tests too. You can change it of course, but I find it does a pretty decent job if you have a large model directing it.

The parent model of course checks the work, but most of the time the handoff is good enough that no edits are needed.

It's also pretty fast and cheap, firing off a bunch of sub-agents to explore different parts of the codebase is a regular occurrence for the way I work.

IME Composer 2.5 is too dumb for any serious coding. Grok 4.6 is twice as expensive (but still much cheaper than Claude Opus) and it does a much much better job.

Composer has improved in last few months. I relied heavily on it last month as ran out tokens and composer free credits were available for use.

Either that, or OpenAI is the most successful NSA psyop.

Were they funded at all by that tech funding wing of the CIA ?

It's the opposite kind of bundling as MoE, which effectively trades memory/storage to save on compute at inference time.