shipping a multi-agent economy on a 3b model
a field report on building a tiny woodland economy with qwen2.5-3b agents, showing how small models can drive emergent market behavior when paired with designed scarcity and sharp prompting.
topic
tools
nemotron 3.5 unifies multimodal safety with custom policies
nvidia releases nemotron 3.5 content safety, a 4b model that combines multimodal input, multilingual support, custom policy enforcement, and auditable reasoning in one inference call.
eva-bench grows to three enterprise voice agent domains
eva-bench data 2.0 adds itsm and healthcare hrsd domains, totaling 213 scenarios across 121 tools to test voice agents on realistic, domain-specific tasks.
hf cli rebuilt for coding agents
hugging face redesigned its hf command-line tool to serve both humans and ai coding agents, cutting token usage by up to 6x on complex tasks.
fine-tune nemotron 3.5 asr for your language or accent
a guide to fine-tuning nvidia's multilingual streaming speech recognition model on custom data for better accuracy in under-resourced languages and domains.
jetbrains releases mellum2, a 12b mixture-of-experts model
jetbrains launches mellum2, an open 12b-parameter mixture-of-experts model optimized for low-latency text and code tasks, activating only 2.5b parameters per token.
reachy mini gets remote mcp tools from hugging face spaces
reachy mini robot can now use remote tools like weather and web search hosted on hugging face spaces via mcp, without downloading code locally.
deepspeed adds muon optimizer support
deepspeed now integrates muon optimizer, reducing memory and improving convergence for large model training.
dpo cuts text degeneration in ocr models
direct preference optimization reduced text degeneration by an average of 59.4% across five ocr model families by using the model's own failure outputs as rejection pairs.
uber caps ai coding tool spending at $1,500 per month
uber limits employee spending on agentic coding tools like claude code and cursor to $1,500 monthly per tool after overshooting its 2026 ai budget.
microsoft releases mai models with low active parameters
microsoft announced two new language models, mai-thinking-1 and mai-code-1-flash, with low active parameter counts and claims of clean training data.
holo3.1 brings fast local computer use agents
holo3.1 expands computer-use ai to mobile, desktop, and web with quantized models for local inference.
microsoft assert tests ai behavior from text descriptions
microsoft's open source assert framework uses ai to turn plain-language rules into scored tests for application-specific ai behavior.
linkedin speeds up extreme-scale optimization with pytorch gpus
linkedin rebuilt its dualip solver in pytorch to handle linear programs with trillions of variables, achieving 75x faster per-iteration times on gpus.
microsoft's agent control spec tames ai behavior
microsoft's new open-source agent control specification gives developers a consistent way to define and enforce policies for ai agents across different environments.
10 github repos for modern database systems and tools
explore 10 open-source github repositories for modern databases, analytics, sql, caching, monitoring, replication, postgresql, sqlite, and ai agent memory.
agent logic guides enterprise ai beyond llms
ibm research shows that adding software primitives like knowledge graphs and program analysis to ai agents improves performance and cuts costs in enterprise workflows.
nvidia cosmos 3 open omni-model for physical ai
nvidia releases cosmos 3, a single open model that generates video, reasons about physics, and predicts actions for robotics and autonomous systems.