I've been thinking of doing this — using one of the "pretty good but not Opus 4.6-good, YET very cheap" models for the implementation part of more basic code features, AFTER first using Opus 4.6 high for the planning stage.

Do you think this would be a decent approach?

Also, which client would I use for this? OpenCode? I don't think Claude Code supports using other models. Thoughts?

I have been doing this and the results have been fairly good.

I use claude to build requirements.md -> implementation.md -> todo.md. Then I tell opencode + openrouter to read those files and follow the todo using a cheap (many times free) model.

It works 90% of the time. The other 10% it will get stuck, in which case I revert to claude.

That has allowed me to stay on the $20/month claude subscription as opposed to the $100.

Not saying anything about the article at-hand, but assuming we were able to detect it with such certainty, I think it would greatly increase the funding, rigor, and breadth or research devoted to finding a cure or treatment that actually worked.

Is this the final straw that kills their platform?

Is this a joke or are they serious with this?

Lol enshittification begins [continues].

It took me way too long to find that (I didn't notice your comment til after).

Sigh at the clickbait headlines.

I might be off-base here, but I get the sense that OP's dysphoria/ennui/ambivalence/Weltschmerz is less about what they're doing as an occupation and more other things that need to be explored more deeply. 27 can be a difficult age with many conflicting/confusing feelings and thoughts, and sorting some of those out might be the key. Again, could be way off-base here — impossible to know from a single short post like this.

Are there any higher-context 70B finetunes yet with good benchmarks?

As well as being a pain to search, it's complete black hole for information.

The trend of more and more projects and companies using Discord as their primary forum for support, docs, and discussion boards is probably not one that will be looked back on as having been a good idea.

I worry that there's so much valuable information stored in prior chats that will simply disappear if Discord ever goes away.

In addition to this, this valuable information is not accessible/searchable via the web without a Discord account. Plus there's the 100 server limit for free accounts, which can become a problem depending on how many projects/communities one is involved with.

That being said, Discord is convenient and cheaper to license/host communities than Slack, which I think is part of the allure.

Does anyone know (or is it publicly known) when the 400B variant will be released?