6. Dynamic Layer Routing in LLMs A retrofittable way to add per-layer routers to frozen LLMs that decide to skip, execute, or repeat each block.
GENERATIVE AI
-
Top AI Papers of the Week: October 13-19
By
–
Top AI Papers of The Week (October 13-19): – Kimi-Dev
– Elastic-Cache
– Hybrid Reinforcement
– Cell2Sentence-Scale 27B
– Holistic Agent Leaderboard
– Dynamic Layer Routing in LLMs
– The Art of Scaling RL Compute for LLMs Read on for more: -
Cell2Sentence-Scale 27B: Converting Gene Expression into AI Training Data
By
–
1. Cell2Sentence-Scale 27B C2S-Scale extends Cell2Sentence by converting gene expression into “cell sentences” and training LLMs on 50M+ cells plus biological text.
-
The rise and fall of Vibe Coding: AI slop reality
By
–
The rise and fall of Vibe Coding: The reality of AI slop https://
search.app/kyhKK #vibecoding #artificial_intelligence #AI #codingforlife #Coding @lexfridman @KirkDBorne @Ronald_vanLoon @erikbryn @antgrasso @sallyeaves @Nicochan33 @HaroldSinnott @mvollmer1 @marcusborba -
How to create AI skills with Claude and YAML structure
By
–
ok but how do you actually BUILD one? for one, you can simply prompt claude: "create a [name of skill] skill, ask me all the necessary questions for context." you can also create it manually. here's the exact structure of a http://
SKILL.md file: 1/ YAML Frontmatter -
Woman Wins Lottery Using ChatGPT-Generated Numbers
By
–
Woman wins lottery using numbers ChatGPT picked for her! https://
search.app/T3V38 #lottery #ChatGPT #LLMs @lexfridman @KirkDBorne @Ronald_vanLoon @erikbryn @antgrasso @sallyeaves @Nicochan33 @HaroldSinnott @mvollmer1 @marcusborba @CatherineAdenle @vinod1975 @YuHelenYu -
Google’s Free Real-Time Voice Agents Course with ADK Gemini
By
–
Google just dropped an ace new course on building real-time voice agents using ADK + Gemini. You’ll learn how to build agents that can search, call APIs, remember context, and talk naturally. 100% free (link in ↓)
-
Reve launches a new video generation model
By
–
Reve prepares to launch a new video generation model in Beta very soon! 720p and 1080p resolution, landscape and portrait formats, sound support. A new contender h/t @VividFeverDrms
-
RemeDi: LLMs Self-Correct Mistakes Through Remasking Mechanism
By
–
LLMs could spot their own mistakes and revise them on the fly. Researchers are tackling this with RemeDi (Remasking-enabled Diffusion Language Model), a new model that introduces a "remasking" mechanism for more flexible text generation. Instead of just predicting tokens,
-
Community-Driven AI Model Marketplaces: Hugging Face and Replicate
By
–
You can find a lot of models for that and more on a community-driven marketplace like Hugging Face or Replicate.