Shimitar@downonthestreet.euEnglish · 16 hours agoThoughts on coding with AI: my experienceplus-squarewiki.gardiol.orgexternal-linkmessage-square3linkfedilinkarrow-up123arrow-down15
arrow-up118arrow-down1external-linkThoughts on coding with AI: my experienceplus-squarewiki.gardiol.orgShimitar@downonthestreet.euEnglish · 16 hours agomessage-square3linkfedilink
ThelastfingerofH@lemmy.worldEnglish · 2 days agoMythos-class model on huggingface: 14T parametersplus-squarehuggingface.coexternal-linkmessage-square12linkfedilinkarrow-up126arrow-down18
arrow-up118arrow-down1external-linkMythos-class model on huggingface: 14T parametersplus-squarehuggingface.coThelastfingerofH@lemmy.worldEnglish · 2 days agomessage-square12linkfedilink
Nzo@lemmy.zipEnglish · 16 hours agoEight LLMs (four open-weight) live in a 24/7 reality show; small open models moderate every lineplus-squarelemmy.zipexternal-linkmessage-square10linkfedilinkarrow-up128arrow-down111
arrow-up117arrow-down1external-linkEight LLMs (four open-weight) live in a 24/7 reality show; small open models moderate every lineplus-squarelemmy.zipNzo@lemmy.zipEnglish · 16 hours agomessage-square10linkfedilink
BeefAndPoultry@lemmus.orgEnglish · 3 days agoHeretic 2.0 released: Model modification for everyone - "it can suppress slop, reduce sycophancy, alter emotional alignment, and pretty much anything else that you can think of"plus-squaregithub.comexternal-linkmessage-square6linkfedilinkarrow-up154arrow-down14
arrow-up150arrow-down1external-linkHeretic 2.0 released: Model modification for everyone - "it can suppress slop, reduce sycophancy, alter emotional alignment, and pretty much anything else that you can think of"plus-squaregithub.comBeefAndPoultry@lemmus.orgEnglish · 3 days agomessage-square6linkfedilink
BeatTakeshi@lemmy.worldEnglish · edit-22 days agoI have a RTX A1000 (8GB) with 64GB DRR5, what would you recommend for a newbie?plus-squaremessage-squaremessage-square28linkfedilinkarrow-up125arrow-down11
arrow-up124arrow-down1message-squareI have a RTX A1000 (8GB) with 64GB DRR5, what would you recommend for a newbie?plus-squareBeatTakeshi@lemmy.worldEnglish · edit-22 days agomessage-square28linkfedilink
Spite_By_Design_LLC@lemmy.dbzer0.comEnglish · edit-22 days agoStarting from Dec, Codex and Chat will share same token pool. Thanks Sam! EABODplus-squaremessage-squaremessage-square15linkfedilinkarrow-up112arrow-down12
arrow-up110arrow-down1message-squareStarting from Dec, Codex and Chat will share same token pool. Thanks Sam! EABODplus-squareSpite_By_Design_LLC@lemmy.dbzer0.comEnglish · edit-22 days agomessage-square15linkfedilink
BeefAndPoultry@lemmus.orgEnglish · edit-23 days agoApparently Gemma 4's chat template can take over 10 seconds just to build the text when there are many tool callsplus-squarehuggingface.coexternal-linkmessage-square2linkfedilinkarrow-up122arrow-down14
arrow-up118arrow-down1external-linkApparently Gemma 4's chat template can take over 10 seconds just to build the text when there are many tool callsplus-squarehuggingface.coBeefAndPoultry@lemmus.orgEnglish · edit-23 days agomessage-square2linkfedilink
xoron@programming.devEnglish · 20 hours agoBrowser-based WebLLM Chatbotplus-squaremessage-squaremessage-square0linkfedilinkarrow-up11arrow-down12
arrow-up1-1arrow-down1message-squareBrowser-based WebLLM Chatbotplus-squarexoron@programming.devEnglish · 20 hours agomessage-square0linkfedilink
Shatur@discuss.tchncs.deEnglish · 5 days agoAnthropic quietly bans recreating existing games in Claude Codeplus-squaretwitee.coexternal-linkmessage-square35linkfedilinkarrow-up1123arrow-down17
arrow-up1116arrow-down1external-linkAnthropic quietly bans recreating existing games in Claude Codeplus-squaretwitee.coShatur@discuss.tchncs.deEnglish · 5 days agomessage-square35linkfedilink
Shatur@discuss.tchncs.deEnglish · 5 days agoSam Altman: "Local inference is a terrible allocation of scarce resources"plus-squaretwitee.coexternal-linkmessage-square174linkfedilinkarrow-up1570arrow-down111
arrow-up1559arrow-down1external-linkSam Altman: "Local inference is a terrible allocation of scarce resources"plus-squaretwitee.coShatur@discuss.tchncs.deEnglish · 5 days agomessage-square174linkfedilink
Shatur@discuss.tchncs.deEnglish · 4 days agoFriends Don't Let Friends Use Ollamaplus-squaresleepingrobots.comexternal-linkmessage-square13linkfedilinkarrow-up1104arrow-down13
arrow-up1101arrow-down1external-linkFriends Don't Let Friends Use Ollamaplus-squaresleepingrobots.comShatur@discuss.tchncs.deEnglish · 4 days agomessage-square13linkfedilink
Shatur@discuss.tchncs.deEnglish · 5 days agoQwen27b vs GPT 6plus-squarediscuss.tchncs.deimagemessage-square10linkfedilinkarrow-up124arrow-down15
arrow-up119arrow-down1imageQwen27b vs GPT 6plus-squarediscuss.tchncs.deShatur@discuss.tchncs.deEnglish · 5 days agomessage-square10linkfedilink
BeefAndPoultry@lemmus.orgEnglish · 6 days agoMistral Says Its AI Model ‘Le Chonk’ Has Leapfrogged China in the Open-Weight Race (1T-A52B)plus-squarewww.wired.comexternal-linkmessage-square23linkfedilinkarrow-up143arrow-down13
arrow-up140arrow-down1external-linkMistral Says Its AI Model ‘Le Chonk’ Has Leapfrogged China in the Open-Weight Race (1T-A52B)plus-squarewww.wired.comBeefAndPoultry@lemmus.orgEnglish · 6 days agomessage-square23linkfedilink
sriram1983007@sh.itjust.worksEnglish · 3 days agoFine-tuned Qwen3-4B locally for one narrow decision — the stablecoin risk-gate side works, the dispute side is where it falls apartplus-squaresh.itjust.worksexternal-linkmessage-square1linkfedilinkarrow-up18arrow-down15
arrow-up13arrow-down1external-linkFine-tuned Qwen3-4B locally for one narrow decision — the stablecoin risk-gate side works, the dispute side is where it falls apartplus-squaresh.itjust.workssriram1983007@sh.itjust.worksEnglish · 3 days agomessage-square1linkfedilink
Shatur@discuss.tchncs.deEnglish · 6 days agoSomeone built a 32-bit RISC-V CPU directly inside Qwen's model weights so it can execute instructions internaly!plus-squarediscuss.tchncs.devideomessage-square3linkfedilinkarrow-up139arrow-down15
arrow-up134arrow-down1videoSomeone built a 32-bit RISC-V CPU directly inside Qwen's model weights so it can execute instructions internaly!plus-squarediscuss.tchncs.deShatur@discuss.tchncs.deEnglish · 6 days agomessage-square3linkfedilink
ImgurRefugee114@reddthat.comEnglish · edit-28 days agoHuh... So... We're here now.plus-squaremessage-squaremessage-square95linkfedilinkarrow-up195arrow-down110
arrow-up185arrow-down1message-squareHuh... So... We're here now.plus-squareImgurRefugee114@reddthat.comEnglish · edit-28 days agomessage-square95linkfedilink
Shatur@discuss.tchncs.deEnglish · 6 days agoApsara conference: Qwen4 next weekplus-squarediscuss.tchncs.deimagemessage-square3linkfedilinkarrow-up147arrow-down14
arrow-up143arrow-down1imageApsara conference: Qwen4 next weekplus-squarediscuss.tchncs.deShatur@discuss.tchncs.deEnglish · 6 days agomessage-square3linkfedilink
Shatur@discuss.tchncs.deEnglish · 6 days agoQwen4 models will have a 1M context windowplus-squaregithub.comexternal-linkmessage-square10linkfedilinkarrow-up147arrow-down11
arrow-up146arrow-down1external-linkQwen4 models will have a 1M context windowplus-squaregithub.comShatur@discuss.tchncs.deEnglish · 6 days agomessage-square10linkfedilink
BeefAndPoultry@lemmus.orgEnglish · 7 days agollama.cpp v0.8.0 adds the LiquidAI LFM3 family, DeepSeek V4.1 Flash, SenseNova U1, Beam, Kolibri-1, Flint, Muse Spark, Granite Switch Decision, and moreplus-squaregithub.comexternal-linkmessage-square14linkfedilinkarrow-up153arrow-down12
arrow-up151arrow-down1external-linkllama.cpp v0.8.0 adds the LiquidAI LFM3 family, DeepSeek V4.1 Flash, SenseNova U1, Beam, Kolibri-1, Flint, Muse Spark, Granite Switch Decision, and moreplus-squaregithub.comBeefAndPoultry@lemmus.orgEnglish · 7 days agomessage-square14linkfedilink
LK Wood IV@lemmy.worldEnglish · 6 days agoMeasured RTX 5080 inference efficiency: 1.20 to 0.32 tokens/joule, with 52–71 W desktop idleplus-squaremessage-squaremessage-square0linkfedilinkarrow-up114arrow-down11
arrow-up113arrow-down1message-squareMeasured RTX 5080 inference efficiency: 1.20 to 0.32 tokens/joule, with 52–71 W desktop idleplus-squareLK Wood IV@lemmy.worldEnglish · 6 days agomessage-square0linkfedilink
