khasky@lemmy.world to Programming@programming.dev · edit-218 hours agoUse DeepSeek behind Claude Code or Codex without changing the coding UIplus-squareimagemessage-square4linkfedilinkarrow-up16arrow-down136
arrow-up1-30arrow-down1imageUse DeepSeek behind Claude Code or Codex without changing the coding UIplus-squarekhasky@lemmy.world to Programming@programming.dev · edit-218 hours agomessage-square4linkfedilink
khasky@lemmy.world to Technology@lemmy.worldEnglish · edit-218 hours agoSomeone built a visualization of what 1 million tokens actually looks likeplus-squareimagemessage-square5linkfedilinkarrow-up143arrow-down124
arrow-up119arrow-down1imageSomeone built a visualization of what 1 million tokens actually looks likeplus-squarekhasky@lemmy.world to Technology@lemmy.worldEnglish · edit-218 hours agomessage-square5linkfedilink
khasky@lemmy.world to Programming@programming.devEnglish · 7 days agoTeamAI puts your team's agent config behind a merge requestplus-squaregithub.comexternal-linkmessage-square1linkfedilinkarrow-up15arrow-down133
arrow-up1-28arrow-down1external-linkTeamAI puts your team's agent config behind a merge requestplus-squaregithub.comkhasky@lemmy.world to Programming@programming.devEnglish · 7 days agomessage-square1linkfedilink
khasky@lemmy.world to Large Language Models@lemmy.worldEnglish · 9 days agoDoes Edge0's 2.9 GB peak for a 35B MoE hold up once the prompt gets long?plus-squaremessage-squaremessage-square0linkfedilinkarrow-up13arrow-down11
arrow-up12arrow-down1message-squareDoes Edge0's 2.9 GB peak for a 35B MoE hold up once the prompt gets long?plus-squarekhasky@lemmy.world to Large Language Models@lemmy.worldEnglish · 9 days agomessage-square0linkfedilink
khasky@lemmy.world to AI@lemmy.ml · edit-29 days agoFaster-than-realtime AI video is turning into interactive televisionplus-squaremessage-squaremessage-square1linkfedilinkarrow-up16arrow-down15
arrow-up11arrow-down1message-squareFaster-than-realtime AI video is turning into interactive televisionplus-squarekhasky@lemmy.world to AI@lemmy.ml · edit-29 days agomessage-square1linkfedilink
khasky@lemmy.world to Machine Learning@lemmy.ml · edit-29 days agoFreeToken claims 39.3 tok/s for Qwen3.6-35B on an 8GB RTX 4060 laptop GPUplus-squaremessage-squaremessage-square1linkfedilinkarrow-up16arrow-down11
arrow-up15arrow-down1message-squareFreeToken claims 39.3 tok/s for Qwen3.6-35B on an 8GB RTX 4060 laptop GPUplus-squarekhasky@lemmy.world to Machine Learning@lemmy.ml · edit-29 days agomessage-square1linkfedilink
khasky@lemmy.world to Anthropic's Claude AI@lemmy.world · 12 days agoAnthropic has a tiny ELI5 Claude skill that turns topics into visual HTML explainersplus-squaremessage-squaremessage-square0linkfedilinkarrow-up12arrow-down111
arrow-up1-9arrow-down1message-squareAnthropic has a tiny ELI5 Claude skill that turns topics into visual HTML explainersplus-squarekhasky@lemmy.world to Anthropic's Claude AI@lemmy.world · 12 days agomessage-square0linkfedilink
