Full-text search across 17145 articles. Combine with topic and date filters; results sorted by relevance.
TypeSafe launched its System One model Jev on September 15, 2026 after two years in stealth, and Convai Innovations open-sourced the competing Laya model under Apache 2.0 three days later, offering agents typed, constrai…
Stack Overflow announced the general availability of Stack Internal on September 30, opening the knowledge-curation platform to anyone via a free Starter workspace at stackinternal.com. The Starter tier connects up to th…
Merj R&D Director Giacomo Zecchini reported that in 100 purpose-built tests, browser agents failed silently on structural, naming, state and feedback defects that accessibility engineering already addresses — including o…
President Donald Trump said he is considering Director of National Intelligence Jay Clayton for a new White House AI czar role and expects to name someone within three or four days, telling Axios that Clayton is "a good …
Google researchers introduced Regularized Recursive Self-Improvement of Agent Harnesses (RRSI), a method that constrains an LLM agent's self-editing of its prompts, control flow, tooling, memory and context management to…
A paper submitted to arXiv on 29 Sep 2026 introduces skill-space shooting, a method that uses foundation model guidance to explore reusable short behaviors, or skills, and convert successful trials into corrective superv…
A September 29, 2026 arXiv paper introduces agentic meta-reasoning, an inference-time harness that makes an agent's control choices an explicit structured reasoning process, with a controller consolidating run state and …
B12 Consulting released Akgentic, an open-source actor-based multi-agent framework for Python 3.12+, available on PyPI as the meta-distribution akgentic-framework. The framework ships eight packages — akgentic-core, akge…
The European Commission plans to triple EU data center capacity from roughly 12 GW to more than 27 GW within five to seven years, requiring an estimated €200 billion in mostly private investment, through the proposed Clo…
A 29 September 2026 arXiv paper presents a black-box secret extraction framework that recovers memorized credentials from commercial API-based LLMs under output-only access. The framework combines Cross-Validated Secret …
A September 29, 2026 arXiv paper reports that an LLM agent translating Triton kernels directly into NVIDIA PTX, a process the authors call "AI lowering," achieved 0.83x to 3.34x the performance of autotuned Triton across…
A developer working across 9 parallel projects with separate Claude sessions advocates a fully terminal-based workflow built on Neovim, Tmux, and Ghostty to cut context-switching friction, noting it took three attempts o…
Researchers Zeyi Liao and colleagues published AmpleGCG, a generative model that learns the distribution of adversarial suffixes from GCG optimization and generates hundreds of jailbreak suffixes per harmful query in sec…
Researchers submitted a paper on 24 Sep 2026 presenting Loom, a tuning-free symbolic compiler framework for tile-based SPMD programs on spatial dataflow architectures. Loom formulates one CP-SAT problem per schedule cand…
Researchers Emiliano Penaloza and co-authors submitted KV-streams to arXiv on 28 Sep 2026, a plug-and-play context-compaction strategy for agentic reinforcement learning that streams the KV cache forward instead of flush…
Researchers submitted TokenCast, a method that learns a composable cost representation for each execution segment of an LLM agent run, forecasting token consumption before and during execution without additional LLM call…
An arXiv paper submitted on 23 Sep 2026 found that participants who read a misleading AI-generated summary of a car-pedestrian accident video accurately recalled the original event only 44.8 percent of the time, versus 8…
A tutorial published by Apify details how to build a documentation chatbot using LangChain, OpenAI, Pinecone, and Apify, with UpCloud's documentation as the example corpus and Streamlit for the chat interface. The guide …
A paper submitted to arXiv on 24 Sep 2026 introduces GAUDI, a geometry-aware conditional diffusion imputer for air-quality time-series data that achieves an RMSE of 0.340 on the ItalyAir benchmark, compared with 0.355 fo…
Researchers submitted AfterVibe, a framework that recovers natural-language specifications from vibe coding sessions, to arXiv on 10 July 2026. AfterVibe uses an LLM to extract an abstract spec from a code artifact and i…