"Slicing and Dicing: Configuring Optimal MoE" MoE models have a huge design space, but most choices are overcomplicated. This paper runs 2,000+ pretraining runs up to 6.6B params and finds the key knobs are mostly expert count and expert granularity. Adding more inactive
AI
-
Research on Steered LLM Activations and Manifold Reachability
By
–
"Steered LLM Activations are Non-Surjective" Activation steering can make an LLM behave very differently, but that doesn't mean any prompt could have caused the same internal state. This paper shows steering pushes activations off the prompt-reachable manifold into
-
The Security Risks of Shadow AI in the Enterprise
By
–
The Shadow AI Crisis — download the report here: https://
josys.com/resources/shad
ow-ai-crisis
… Summary:
Shadow AI use is rampant, with 78% of professionals using AI tools in their daily workflows. Yet 70% of organizations lack visibility into these tools, creating significant data exposure risks. -
Training AI models with handwritten data
By
–
we should train the AI models by letting them write things by hand
-
Multi-agent system that iterates on game mechanics
By
–
Can AI truly iterate on game mechanics, not just generate one-off code? CreativeGame Team (Univ. of Bristol, SJTU, Shandong Univ., Nanjing Univ., Sreal AI) built a multi‑agent system that treats game mechanics as explicit objects. It uses programmatic rewards (not subjective
-
AI-driven job shifts may increase in-house developer hiring
By
–
Its a reason why there may be increased demand for some jobs disrupted by AI: when your local midsized insurance broker wanted software, there was no way they could even consider building internally. Now it may be worth getting a few in-house developers & let them solve problems.
-
SmallCode: A Terminal-Native Coding Agent for Local AI Models
By
–
SmallCode is a terminal-native coding agent designed from the ground up to extract useful work from local models (7B-20B) running on consumer hardware.
-
Firms insourcing work to capture AI productivity gains
By
–
One trend that I think you might start to see at big companies is insourcing via hiring: why pay so many outside vendors (legal, marketing, software vendors) when you can hire in-house and harness AI productivity gains yourself? Talked to executives already going this route…
-
Running local terminal AI agents with Ollama
By
–
It runs locally without any cost. SmallCode is not a model. It's a terminal agent. Here's Gemma 4 model on @ollama
: https://
ollama.com/library/gemma4 I'd suggest to read the post before commenting LOL -
Local AI coding agent workflow with Hermes orchestrator
By
–
LOCAL AI coding agent finally make sense with Hermes orchestrator. Hermes routes work through Kanban. SmallCode uses Ollama models on a Mac mini for scoped patches, tests, and repo cleanup. Claude and Codex do the heavy lifting. All of it tracked in a single Kanban board.