Well back ok the saddle after some deserving rest.
Any conversation
A thing I've been doing lately is trying to come to the same conclusions others have without looking their the direct techniques and code. Last night I tried to figure out why people do vector based retrieval for RAG and ended up running these experiments: n0tls.com/โฆ/2026-09-03-i-think-โฆrag-with-grep.html
I'm still going to do an explore agent.
az interneten nem lehet egy kรฉpet sem รกtmรฉretezni, sem Windows alatt, a Grok is csak hozzรกvetลlegesen dolgozik, mi kรถvetkezik ebbลl, muszรกj lesz beengedni Gemmรกt, mintha Linus Thorvalds a napokban panaszkodott volna, hogy a Linuxot is elรกrasztotta az ai
You can't resize an image on the internet, not even under Windows, Grok only works roughly, what follows from this, we'll have to let Gemma in, as if Linus Thorvalds had complained the other day that Linux was also flooded with AI
ๅฏนไบๆดไธชไบ่็ฝๅๅฒ๏ผๆๅฏ่ฏดๅบๆฌไธๆฏไธไธชๆ่ง่
๏ผๆไธ็ดๅจๆถ่ดนๅ
ๅฎน๏ผไฝๆฏๆฒกๆ็ไบง่ฟไปไนๅ
ๅฎน๏ผไบ่็ฝไธๆฒกๆๆ็็่ฟน๏ผ่ฟๆฏๆๅคๅๆ๏ผๅ ไธบไธญๅฝ็่บซไปฝๅๅ
ๅฎนๆฟ็ญ
Regarding the entire history of the internet, I can say I've been largely an observer. I've always consumed content, but I haven't produced any. There's no trace of me on the internet, which is an unforeseen consequence due to China's identity and content policies.
I notice that language models are much better at programming than at writing. This is largely because, in programming, they have a closed feedback loop that allows them to find errors. Writing is much more complicated because the feedback is much more diffuse and delayed over time. In fact, it is often not well-defined.


