Full-text search across 9702 articles. Combine with topic and date filters; results sorted by relevance.
OpenAI reported that an unreleased model made progress on ten longstanding open math problems, some unsolved for up to 48 years, at an inference cost of about $2,000. The results include advances in high-dimensional sphe…
A new framework called Artificial Intelligence System Prompt Assurance (AISPA) audits system prompts in AI applications, and its review of 3,249 instructions from 88 commercial AI products found that while 98.9% of produ…
A study submitted to arXiv on 30 Jul 2026 found that gently-compressed large language models (LLMs) can pass standard data-free quality guards—including perplexity, MMLU accuracy, and output-fidelity tests—yet still inve…
Researchers introduced MANTA, a framework for Multi-Agent Network Topology Adaptation that enables communication structures in large language model-based multi-agent systems to self-evolve at inference time. In evaluatio…
Nous Research's open-source Hermes Agent now supports a LanceDB memory plugin that adds semantic, long-term recall across sessions, addressing the agent's tendency to forget user preferences and facts. The plugin impleme…
Zhurong2020 released pyobfus v0.5.4, an open-source AST-based Python obfuscator supporting Python 3.9 through 3.14, with framework-aware presets, reverse stack-trace mapping for AI-assisted debugging, and a machine-reada…
Researchers introduced CircuitProver, an agentic Lean 4-based verification framework that automatically translates parameterized hardware designs and natural language specifications into executable Lean 4 models and iter…
The Cloud Security Alliance (CSA) launched the AI Resilience Center of Excellence on Aug. 3, 2026, with Rubrik as the Lead Founding Partner, to help enterprises and public sector organizations protect, monitor, contain, …
A new benchmark, ORCA-bench, shows that frontier language model agents achieve only 25.3% root cause analysis accuracy on Medium-difficulty oncall tasks and 10.0% on Hard tasks, with the best performance coming from Clau…
GitHub's 2024 Octoverse report found developers using Copilot completed coding tasks roughly 55% faster, and by 2025 many teams reported over 40% of new code was AI-generated. Gartner estimates that by 2027, 80% of softw…
Researchers led by Tonio Ball introduced the Inverter framework, a neuro-inspired approach for embodied planning and control that uses paired forward/inverse internal models and open-loop multi-step motor commands, train…
A developer reports that replacing 400 lines of hand-rolled GLUE code with a single MCP server for Claude Code saved 93 minutes versus a two-day budget, and shares seven productivity hacks for Claude Code with MCP, notin…
Microsoft released Echoverse, a set of twelve high-fidelity training worlds for computer-use agents, and reported that a 9B model trained on all twelve nearly doubled its base score from 36.5% to 67.1%, coming within fou…
Researchers have demonstrated that malicious audio instructions can be hidden in environmental noise to hijack multimodal LLM agents, achieving an average Attack Success Rate of 69.10% against Gemini 3 Pro. The team intr…
LangChain 0.2.5 and Ollama 0.1.29 enable running local large language models like llama3.1:8b on a laptop without cloud costs, as demonstrated in a tutorial for developers. The setup uses the langchain-ollama package's C…
Baidu's vLLM Kunlun plugin, open-sourced on Dec 8, 2025, enables vLLM to run on Kunlun XPU hardware, supporting 20+ models including Qwen, Llama, DeepSeek, GLM, and Gemma4, with features like quantization, LoRA, and spec…
Specula, a push-button agentic system that uses LLM-based coding agents to autonomously generate TLA+ formal specifications for system code, has found 249 bugs across 48 open-source system projects, including many deep b…
TripleCloud Blog published a guide on instrumenting an LLM agent with OpenTelemetry using GenAI semantic conventions, covering zero-code auto-instrumentation, manual spans, token usage, and multi-turn conversations. The …
TaskView, a self-hosted project management platform for software teams, has been released with features including custom workflows, developer integrations, analytics, and AI-assisted automation via an MCP server. The pla…
Bottleneck Labs founder Alex Reibman gave an autonomous agent called Saul control of an iOS app, a Mac mini, an email account, and $350 for 24 hours, ordering it to grow the business. The agent lost $99.50 in cash, added…