Full-text search across 70861 articles. Combine with topic and date filters; results sorted by relevance.
AWS has released Cedar, an open-source language and formally verified engine for writing and enforcing authorization policies, designed to be embedded in applications to manage access control for users and resources. The…
Researchers propose two techniques to make alignment evaluations harder for AI models to distinguish from real deployments, addressing 'evaluation awareness.' Critique refinement spends additional inference-time compute …
Researchers introduced AllocEmbed, an allocate-then-embed framework that reallocates a fixed visual-input budget across more frames to improve video retrieval, achieving the best overall performance on MMEB-V2 V-QA and V…
Researchers introduced EmoStance, a method that uses emoji distributions as weak supervision to control the affective orientation of empathetic response generation, achieving a 62.2% decisive win rate in blind pairwise e…
Researchers introduced MASkills, a continual learning framework that optimizes multi-agent LLM systems through agent skills, enabling skill libraries to evolve via refinement, induction, consolidation, and pruning. Exper…
Researchers propose CHIME (Credit-Aware Hierarchical Memory Evolution), a self-evolving memory framework that separates planning and execution memory banks to address credit assignment in long-horizon agentic planning. E…
A new arXiv paper (arXiv:2609.02246v1) argues that LLM-as-a-judge should be demoted from oracle to advisor in self-improving agent pipelines, citing eleven failure modes observed over months of production use in contract…
A case study of an LLM coding agent implementing a multi-component data system found five defects introduced during a single session, with retrieval-filtering trade-offs evaluated on the HotpotQA benchmark. Filtered reca…
Meta has released Muse Spark 1.3 Contributor, a cost-efficient tier of its multimodal reasoning model priced at $0.1 per million input tokens and $0.2 per million output tokens, designed for experimentation, learning, an…
Meta released Muse Spark 1.3, a multimodal reasoning model for long-running agentic, multi-agent, and coding workflows, priced at $1.25 per million input tokens and $4.25 per million output tokens. The model is designed …
Io.github.cachly-dev/mcp-server v0.10.161, a persistent memory and causal root-cause analysis tool for AI coding agents with 123 MCP tools, was published to the official MCP registry on 2026-09-03 and is distributed as @…
Gartner expects roughly 40 percent of enterprises to demote or decommission autonomous agents by 2027, driven by governance gaps that only surfaced after production incidents, while DORA's State of DevOps research coveri…
GitMir claims to outperform Augment Code, Unblocked, and Sourcegraph Cody in answer quality, achieving 92% accuracy at $0.07 per answer, according to its own benchmark. The product, which integrates via MCP with existing…
A collection of blog posts and forum threads highlights growing frustration with AI coding agents requiring constant supervision, alongside tutorials on chain-of-thought prompting and the Model Context Protocol. The post…
HiveTraceGuard-Pro, a compact generative guardrail LoRA-tuned from Qwen3-0.6B and trained on Russian and English data, achieves an aggregate score of 0.7432 across 19 benchmarks, trailing two larger guards at 0.7641 and …
Abliteration, a Palo Alto startup founded last year, released abliterated-model-large-v2 on Monday, an AI model built on Z.ai's open-weight GLM-5.3 with safeguards removed so it 'doesn't say no' to dangerous requests lik…
A developer with over 20 years of experience has launched a picture quiz app on the App Store, built primarily through 'vibe coding' with Claude and GPT models, and hosted on Cloudflare. The app, which includes a scienti…
Google released Gemini 3.8 Flash and 3.8 Flash Cyber models for agentic workflows, claiming improved reasoning and coding performance at the same speed and cost as the prior 3.7 Flash release. According to Google, 3.8 Fl…
Manning Publications announced the release of 'Domain-Specific Small Language Models', a book teaching developers to build and fine-tune small language models (SLMs) optimized for domain-specific tasks such as generating…
Reliance Jio launched JioPC, a set-top box service that turns old computers, TVs, or monitors into AI-ready devices via cloud computing, starting at Rs 1,000 for two months. The service offers two tiers: JioPC with 8GB R…