I read
Still trying to figure out the boundaries of these tools' strengths without outsourcing important thinking, problem-solving, and the collective building-up of a mental model of the systems we're developing.
The shape of LLM tools as toolsโfit for a purpose, ergonomicโis becoming clearer, and human patterns of behavior with them that do more harm than good are also becoming easier to recognize.
Any conversation
็ๆฅๅฏไปฅๅไธญๆใๅ ไธบๆฒกๆ่บซไปฝ่ฏ๏ผๆไปฅไธ่ฝๆฅๆๆๆบๅท๏ผๆฅ็ไธ่ฝๆณจๅ็จณๅฎ็email๏ผไนๅฐฑๆฒกๆณๆณจๅๅ
ๅฎนๅนณๅฐ๏ผๅๅธๅ
ๅฎนใhotmailๅ ไธบๆๆฒกๆ็จณๅฎ็ipๅฐๅ๏ผๅธธๅธธๅฐ็ฆๆ็email่ดฆๅท๏ผๆ็mastodon่ดฆๅทๅ ๆญคไนๆฒกๆณ้ฟๆไฝฟ็จใๆๅธๆ่ฟๆฏไธไธชๆๅฏไปฅ้ฟๆๅๅธๅ
ๅฎน็ๅฐๆน
It seems I can post in Chinese. Because I don't have an ID card, I can't have a phone number, and therefore can't register a stable email address, which means I can't register on content platforms or publish content. Hotmail frequently blocks my email account because I don't have a stable IP address, so my Mastodon account can't be used long-term. I hope this is a place where I can publish content consistently.
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.


