Foresight
blog.evanchen.cc·15h
🕹Game development
Flag this post
Explorable explorable explanations
blog.khinsen.net·10h
🕹Game development
Flag this post
<![CDATA[ Agentic Plan Execution ]]>
dolthub.com·2d
🕹Game development
Flag this post
AI Wealth Managers and Smart Contracts = Dead People Controlling Money Forever
⚙Engineering
Flag this post
Bridging the AI divide: How Frontier firms are transforming business
blogs.microsoft.com·19h
⚙Engineering
Flag this post
FaithAct: Faithfulness Planning and Acting in MLLMs
arxiv.org·5h
🕹Game development
Flag this post
Textual Self-attention Network: Test-Time Preference Optimization through Textual Gradient-based Attention
arxiv.org·1d
🕹Game development
Flag this post
Fixing Enterprise Apps with AI: The T+n Problem
oreilly.com·1d
🕹Game development
Flag this post
Spilling the Beans: Teaching LLMs to Self-Report Their Hidden Objectives
arxiv.org·1d
🕹Game development
Flag this post
AdvisingWise: Supporting Academic Advising in Higher Educations Through a Human-in-the-Loop Multi-Agent Framework
arxiv.org·1d
🕹Game development
Flag this post
BIPPO: Budget-Aware Independent PPO for Energy-Efficient Federated Learning Services
arxiv.org·5h
🕹Game development
Flag this post
Pluralistic Behavior Suite: Stress-Testing Multi-Turn Adherence to Custom Behavioral Policies
arxiv.org·2d
🕹Game development
Flag this post
Show HN: I have zero dev experience and built a 220k LOC fintech SaaS with AI
🕹Game development
Flag this post
Procedural Knowledge Improves Agentic LLM Workflows
arxiv.org·5h
🕹Game development
Flag this post
DANS-KGC: Diffusion Based Adaptive Negative Sampling for Knowledge Graph Completion
arxiv.org·5h
⚙Engineering
Flag this post
Forgetful giants versus personal confidants: how SSMs could reshape the AI market.
🕹Game development
Flag this post
SofT-GRPO: Surpassing Discrete-Token LLM Reinforcement Learning via Gumbel-Reparameterized Soft-Thinking Policy Optimization
arxiv.org·1d
🕹Game development
Flag this post
Beyond Models and Compute: Big Tech’s AI Moves
pymnts.com·6h
🕹Game development
Flag this post
AgentExpt: Automating AI Experiment Design with LLM-based Resource Retrieval Agent
arxiv.org·2d
⚙Engineering
Flag this post
Loading...Loading more...