Off topic:With sol pricing drop tbh kimi k3’s value prop has not been that great. For our internal use case/testing/benchmarks sol come out with way better quality and much cheaper costs.
Kimi really needs to drop their pricing (I heard it’s set by them across all the neoclouds)
Sol is at 2/10 vs kimi’s 3/15
Sol pricing dropped but so did the quality few days ago. I wonder when these companies are sued for making the terms from their side to go downwards while taking the same subscription cost.
I am glad I am not the only one to notice. I feel like I've gone back to Sonnet 4 levels of incompetence!
With Sol 6 I am back in a world where the model writes bad code because it is lazy ("You're absolutely right, I did not [do it properly] because I did not want to edit [a normal amount of files]").
- it actually failed to correctly understand a simple English grammar and logical implication of it, then when challenged it admitted its mistake but couldn't explain why it made it.
- for the code I am working on, I asked to create two PRs for the two small features (couple lines of code). It created one in upstream, as intended, and other one in my own fork. Just like that, out of nowhere, and called the job done.
- it said it would ask me to approve/ammend the suggested PR message, it never did and fired off right away
- it keeps forgetting the changes it did itself; no context compaction was used
- it said it tested the change visually, but it did not even try
On top of that, it ignores all of my AGENTS.md, which is short and concise. I mean I point it at ignoring it, it acknowledges and ignores again.
This is astonishingly bad and it is nowhere close to Sol 5.6, or even DeepSeek 4.1! I swear even Gemini 3.8 is slightly better.
To me, Sol6 is what Opus5 was for Claude.
I keep saying that with self-hosting, you at least know what to expect and don't have to trust they nerf their models as they go. I was a skeptic and considered nerfing a conspiracy theory, but at this point with enough experience, I have experienced enough to fully see this being a thing.
Probably only a matter of time before some class action happens.
netvarun · · focus · HN ↗
nicce · · focus · HN ↗
koyote · · focus · HN ↗
With Sol 6 I am back in a world where the model writes bad code because it is lazy ("You're absolutely right, I did not [do it properly] because I did not want to edit [a normal amount of files]").
cromka · · focus · HN ↗
- it actually failed to correctly understand a simple English grammar and logical implication of it, then when challenged it admitted its mistake but couldn't explain why it made it.
- for the code I am working on, I asked to create two PRs for the two small features (couple lines of code). It created one in upstream, as intended, and other one in my own fork. Just like that, out of nowhere, and called the job done.
- it said it would ask me to approve/ammend the suggested PR message, it never did and fired off right away
- it keeps forgetting the changes it did itself; no context compaction was used
- it said it tested the change visually, but it did not even try
On top of that, it ignores all of my AGENTS.md, which is short and concise. I mean I point it at ignoring it, it acknowledges and ignores again.
This is astonishingly bad and it is nowhere close to Sol 5.6, or even DeepSeek 4.1! I swear even Gemini 3.8 is slightly better.
To me, Sol6 is what Opus5 was for Claude.
I keep saying that with self-hosting, you at least know what to expect and don't have to trust they nerf their models as they go. I was a skeptic and considered nerfing a conspiracy theory, but at this point with enough experience, I have experienced enough to fully see this being a thing.
Probably only a matter of time before some class action happens.