@Xaviancrypto Around 150k to emigrate from Germany to Sweden and just code in the middle of nowhere with some peace and quiet lol. shooting a little high I guess. 15-20k to put proper solar panels on my parents roof would also go a long way.
@bridgemindai Ranking Muse as low as it is must be a skill issue. It's certainly benchmaxxed, but I have worked extensively with GPT models, Muse and GLM and disagree with your ranking. Muse is definitely better than GLM flash and much faster as well. I would put it 1st in C or last in B.
So, I finally tested GPT-6 Astra.
2 real repos, 105 bugs, find and fix what you can. Max effort:
GPT-6 Astra: 48/105
Fable 5.1: 43/105
GPT-5.6 Sol: 42/105
Gemini 3.8 Flash: 20/105
And it's crazy efficient. Look at the time and cost π§΅
@thsottiaux Tibo, the instant limit stop in the middle of tasks is hurting my workflow so incredibly much. I hate the people who abused the before state, but could you guys maybe reinstate it for Luna-Threads at least? Nobody uses Luna for long horizon tasks, so abuse should be way lower.
@TJeparskis 59% with 20min read only on sol high, no other task running. sol is not for Plus users anymore. For the first time ever I am considering canceling my oAI sub and trying something new. Any suggestions for someone who is poor but used to Sol high level?