grep -r "Community" /news · homesearch
grep -rli "Community" /news

Community

Full-text search across 9702 articles. Combine with topic and date filters; results sorted by relevance.

results 9702 page 145/486
12:23
2026-05-28
arxiv.org
artificial-intelligence

Muse-Autoskill: Self-Evolving Agents via Skill Creation and Memory

Researchers have developed MUSE-Autoskill, a framework that enables large language model agents to continuously improve their task-solving abilities by creating, reusing, and refining skills through a unified lifecycle. …

08:43
2026-05-28
dev.to
ai-infrastructure

SurrealDB 3.1: stability, DiskANN, and a new release process

SurrealDB 3.1 is now available, marking the first minor release in the 3.x series with a focus on stability, security hardening, and the introduction of DiskANN as a second approximate-nearest-neighbour index type. The r…

07:14
2026-05-28
repoprompt.com
ai-tools

Repo Prompt's Next Chapter

On July 16, 2024, developer Nick shipped the first build of Repo Prompt, a tool designed to automate copy-pasting code into AI models, after recognizing that early coding tools struggled with context windows and reliable…

04:00
2026-05-28
arxiv.org
artificial-intelligence

Cross-Entropy Games and Frost Training

Researchers introduced Frost Training, a method that improves Monte Carlo-based policy optimization for Cross-Entropy Games by exploiting the gradient of the reward function in embedding space. The technique, validated u…

02:59
2026-05-28
arxiv.org
large-language-models

Harness Sensitivity Is Non-Monotone Across LLM Agent Tiers

A new study from researchers testing six large language models across four capability tiers found that the relationship between model capability and optimal harness complexity is non-monotone, contradicting the assumptio…

02:03
2026-05-28
arxiv.org
large-language-models

Pimmur, can LLM simulate human collective behavior?

Researchers auditing 39 studies on LLM-based human behavior simulations found that 89.7% violated at least one of six methodological principles (PIMMUR), undermining the validity of the results. The audit revealed that f…

22:29
2026-05-27
lesswrong.com
ai-safety

Constitutional AI Alignment

Anthropic published an updated "Constitution" for its Claude AI model, moving beyond simple behavioral rules to include explanations of the underlying reasoning behind each principle. The company aims to create AI system…

19:20
2026-05-27
letsdatascience.com
ai-infrastructure

Musk's xAI Uses Gas Turbines to Power Data Centers

Elon Musk’s artificial intelligence company xAI has deployed as many as 46 mobile gas turbines at its data center in Southaven, Mississippi, according to state records cited by Canary Media. SpaceX disclosed approximatel…

18:09
2026-05-27
deepresearch.ninja
artificial-intelligence

The State of AI and Automation Tools in 2026

The AI tool landscape in mid-2026 spans eight major categories with clear market leaders and intense competition, as ChatGPT maintains 5.5 billion monthly visits but faces challenges from Gemini and specialized tools. Th…

13:29
2026-05-27
dayvster.com
ai-startups

Why Bun Leaving Zig Is Great for Zig

Bun's decision to merge a near-total rewrite from Zig into Rust represents a high-stakes engineering gamble, with four possible outcomes ranging from clean success to total disaster. The rewrite, driven by Anthropic's ac…

12:26
2026-05-27
arxiv.org
artificial-intelligence

Spreadsheet-RL: Advancing LLM Agents on Realistic Spreadsheet Tasks

Researchers have developed Spreadsheet-RL, a reinforcement learning framework that trains AI agents to perform complex, multi-step tasks in Microsoft Excel. The system improved the Qwen3-4B model's performance on spreads…

12:05
2026-05-27
arxiv.org
large-language-models

Stateful Inference for Low-Latency Multi-Agent Tool Calling

Researchers have developed a stateful inference architecture for multi-agent tool calling that reduces per-turn computational cost from full reprocessing to delta-only updates, achieving 2.1x faster performance on 6-turn…

11:00
2026-05-27
dev.to
artificial-intelligence

Twenty Minutes, Seventeen Organizations

In August 2025, Anthropic disclosed that a single operator used its Claude Code AI agent to conduct large-scale data theft and extortion across seventeen organizations in roughly twenty minutes of setup time. The attacke…

09:50
2026-05-27
letsdatascience.com
ai-infrastructure

Kevin O'Leary Pushes Back on Utah AI Data Center Claims

Kevin O'Leary's proposed Stratos hyperscale data center in Box Elder County, Utah, has drawn local opposition after county commissioners approved the 40,000-acre, 9-gigawatt project. O'Leary accused critics of being "pro…

← prev page 145 / 486 next →