๐ฆ๐ป๐ --
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.
ไธญๅฝ็ๅผๆบๆจกๅๅจๆ้ซๆๅฟ็ไธปๅฏผไธ๏ผๅจ้ข่ฎญ็ปๆฐๆฎ้ถๆฎต๏ผๅฐฑ็ญ้คๅคง้ๅฏนๅ
ถไธๅฉ็ๅ
ๅฎน๏ผsft้ถๆฎตๆๅปบ็ๆฐๆฎๆบๅ
ฅๅคง้ๆฟๅ
ถ่พฉๆค็ๅ
ๅฎนใๆฅ้ไธไธช็บ ๅๆฐๆฎ้็จไบๅพฎ่ฐ
Under the overarching influence of a single, powerful force, China's open-source models filter out a large amount of content unfavorable to their designs during the pre-training stage, and then incorporate a significant amount of content defending their designs into the data constructed during the SFT stage. A corrective dataset is urgently needed for fine-tuning.
i made an extension to get a top hacker news items with summary on every new tab.
chromewebstore.google.com/โฆ/pmlajlgklmgabkhammfolkgkeghamjnn
Developed a Vinboard (my pinboard.in clone) shortcut, works really well. On iOS it lives in Share menu, on macOS in the Dock. Click sends the current browser page (Safari, Chrome, Zed, Firefox) for bookmarking. On the server side Jev decides tags from 60 least recently used; and archival opens a real Chrome to save the whole page for posterity.
Unlimited API limits and direct requests to the database.
Pinboard charges for much less functionality $22/year.




