Model collapse isn't a genuine threat
LLMS
-
Model Limitations: Why AI Cannot Generate Ungrounded Content
By
–
That would be a model that couldn't answer the prompt "write me a story where a walrus teaches me the basic ideas of particle physics" Because a Walrus never said those things!
-
Alibaba Releases Qwen3-Omni Multimodal AI Model
By
–
China will always stay one step ahead of the U.S. in AI Alibaba just dropped Qwen3-Omni and it's the first model that doesn't sacrifice anything to be multimodal. Usually when you add vision and audio to a language model, text performance tanks. Not here. Qwen3-Omni-30B-A3B
-
DeepSeek Terminus: Next-Level Hybrid AI Model Launch
By
–
DeepSeek just dropped Terminus: The next level hybrid model. https://
search.app/5bkKm #DeepSeek #Terminus # @sonu_monika @enilev @Jagersbergknut @TysonLester @chidambara09 @labordeolivier @BetaMoroney @tlloydjones @Nicochan33 @jeancayeux @RLDI_Lamy @pierrepinna @pierrecappelli -
Alibaba’s Rapid Rise Competing with Frontier AI Models
By
–
Alibaba, which now competes with the big frontier models, wasn't on my bingo card. It's absolutely crazy, you can hardly keep up. New releases every day, benchmarks maxed every day.
-
PrimeIntellect and willccbb launch hands-on RL environments workshop
By
–
> i want @PrimeIntellect and @willccbb running a hands-on RL environments workshop, with opensource models hosted directly on their infra there's so much possible this is what focusing on Local AI should look like
-
Open-Source AI Tools: RunPod, OpenRouter, and Local Function Calling
By
–
> i want @runpod
, @openrouter
, and many more to show how they've made it so easy to tinker with open-source AI > i want someone to break down the openai api > i want local function calling, live, with open models -
Open-source LLMs platform demo from millions to 100B parameters
By
–
> i want @huggingface to demo how literally every open-source llm-from a few million params to 100b+-runs on their platform: streamed, quantized, fine-tuned, deployed. everything working, everything open, everything awesome
-
Aphrodite Engine, Inference & Quantization Talk Series
By
–
> i want @AlpinDale to give a talk on Aphrodite Engine & Inference Engines
> and maybe another one on Samplers > i want @casper_hansen_ to break down quantization and how he built AWQ -
Dynamic Quantization and Fine-tuning Sessions with Unsloth and DSPy
By
–
> i want @UnslothAI and @danielhanchen to do a full session on dynamic quant
> and a separate one on fine-tuning > i want @DSPyOSS and @lateinteraction to make the case for DSPy's adoption