My main issue with rtk is that rtk randomly messes modification and agent start polling same tool continuously.

Sweden main issue is that there is no transmission capacity between North and South, like now prices are 2x at south.

The government that keeps rejecting offshore wind for bogus security reasons is probably a bigger factor.

Those wind farms would have connected into the zones with the highest prices.

They've rejected an amount that would generate more than the entire grid usage. Or way more than double what the cheap zones generate from their 2/3rds hydro and 1/3rd wind.

On one hand Swedish government rejected applications for 11 offshore wind sites on national security grounds, on the other hand, wind investors state that they will not do wind investments in Sweden without subsidies.

" risk-sharing mechanism will be required, for example through two-sided Contracts for Difference and state-backed credit guarantees that reduce investment risk and unlock project financing.”

https://www.renews.biz/offshore-wind/skyborn-calls-for-swedi...

That's due to shutting down reactors in the south. Turns out "transmission capacity" is more complicated than having fat wires...

Shutting down => Not building new ones. All decommissioned reactors would have reached EOL by 2025 anyhow.

Swedens main issue is a political class disconnected from reality.

That is a global issue.

Pretty much every reply to the parent has now given a very different reason for why the problem exists. Anyone else want to give it a try? Bonus points for mentioning meatballs and/or lutfisk.

How is that a thing when the entirety of Finland is a single pricing zone?

Yup and this propagates those clumsy if this_new_code_branch: actual_code_that_matters else: old_legacy_code_that_should_not_be_there

Yup, new SOTA models especially with high/xhigh/max reasoning too often overengineer solutions, good for benchmarks that usually measure task completion, bad for normal development where you don't want 'rewrite in rust and 1k LOC unit tests' style solutions when agent does mundane bug fixes.

When it comes to mundane bug fixes the value is in actually finding the cause of the bug, and I find SOTA models way outperform smaller ones here. I don't care about their output - I can write the correct 5 line patch myself once I understand what's wrong.

Mistral just needs to good enough category think all those flash models or Qwen3.8 27b which they sadly aren't at the moment, that plus being European lab will mean that they will have very nice business. Even now these SOTA models feel too overkill for most tasks.

Yup like you go far enought you will pick lots of transferable skills like data cleaning in the case of LLM, DOM parsing case of web browser or welding case of rocket.

Big corporations there is politics on play and too often you see CABs and other bureaucratic stuff instead of checkboxes for gated releases, 2FA etc.

I have noticed that these cheaper and faster models are very great for Ops-work. Luna max is beast when you use some stronger model to write detailed instructions/run book what to do and when to stop.

But it was Google fault that they really cannot productize all that innovation that happened DeepMind. Google probably now fumbled with world models and this exodus will create next giant in that space.

> Google probably now fumbled with world models [...].

Can you explain this more precisely?

Speed play also you can get much faster responses with 9b model.