I hope all the best to succeed with this project, I'm sold!

Source: I bought the same (with core i7, so it's performant, etc.).

The problem with the "The Most Infuriating Answer" is that it entirely neglects facts, and only those say it who do have a good experience with it.

Happy for you, internet stranger. Just like I am happy for all of those around me: you all are the ones who do good parenting.

In case you also want to become a better person in general, I recommend to stop being condescending, and not to say this ever again to anyone. You hurt more than you think you are wise.

Go and compare them. I love getting lost in data, and I was happy to see all the overloaded, very badly curated, non-dynamic OpenRailwayMap. I cannot click on a railway to get more info, the electrification map is just a mess of many similarly shaded colors. Not user friendly, even if it _has_ the data, it is unfriendly to the user, and makes exploration hard.

I say this as an OSM enthusiast and contributor.

Compare this to the "AI slop"; even though at first I ran into a misinformation (Zambia central links to London Central), it still made me stay on the page and explore some scenic routes. I obviously knew that this is NOT all the railways, but something fun to engage with and maybe even learn / explore some new things, hell maybe start planning my winter vacation.

I guess what I am saying is: your comment has no added value, just sourness, negativity.

I hope the author keeps iterating on this project, eventually make it more OSM-interconnected, fix the tiny bugs and focus on bringing joy to us who are interested. After all, this product is out in public now, whereas your miserable comment will get buried here for good.

Last night it single handedly implemented a feature after a grilling session, and came back with the red-yellow-green risk assessment points that I mostly saw with anthropic models. I had to check if I'm using the right model, but it was DS4Flash.

So maybe I was using it already?

To be more constructive, what I did (as an experiencd SWE but a complete noob to agentic coding): went to pi.dev's extension marketplace and looked into all the new shiny stuff. Subagents, mcps, context and memory optimizers, skills. Using the most popular ones (not necessarily the best ones)

It was like 15years ago learning the new mindset of vim (and spending a ton of time to customize it to my workflow). My understanding is that Claude and opencode doesn't give you this flexibility.

Learning all these stuff drove me to also set up openwebui, and it was such a successful private project that I implemented it at work (with jira/confluence/bazel query access) and management said "we need this by tomorrow".

I believe the models matter not that much anymore. The "harness" does. (unless you just want to vibe code. Thebn, throw crap at fable and call it a day)

(TBH though, in my multi-subagent workflow I do use other, more expensive models for planning, reviewing, oracle-ing)

I haven't used our slow opus subscription for weeks.

(Also set up an OpenWebUi self-hosted chat that works from my phone, has some mcp and skills. fully replaced perplexity. Monthly cost ~$18 for hosting and subscriptions)

The software itself is magic, kudos to all the developers and community.

Hmmm, I remember this from the past, but one of my adblock rules probably catches this one, I haven't experienced it for years.

I use it from pi.dev as well through the OpenCode Go $10 subscription ($5 first month).

Used more than 20M tokens at a cost of ~$20 (up to $60 is included in the $5 plan) Out of which deepseek pro had ~200 messages which is around 1.5M tokens (10+M cached)

32G RAM, nvme 1TB, core ultra 258V.

Looking at the prices now... Wow, was I lucky.

Tried some of the 7b models locally, more than usable, around 30token/sec, not with the NPU, but using the ARC integrated GPU.

I am a noob for this, but I guess it's time to experiment more with this local setup

Regardless, the technology itself is amazing, and eventually should (will) be common infrastructure

Aconfmgr is a good solution (practical trade-off for me). When it feel like "my OS must be dirty at this point", then I spend a couple minutes with this and I'm back to the clean state.

I don't do this more then twice a year, so if you insist on an always clean system, YMMV

App still working tho.

Clothing is the worst offender here. Impossible to recycle. The quality would not be good enough and the price is too high. It is a huge waste of resources.

Upcycling (e.g. repurposing) works with some materials, though, however, with very low efficiency.

Europe is moving towards reducing fast fashion therefore. This is a good thing in general, but I don't see this change in the US / Asia. And very slowly also in Europe.

I do some stuff with gemini flash and Aider, but mostly because I want to avoid locking myself into a walled garden of models, UIs and company

[1]: https://github.com/libre-tube/LibreTube