Full-text search across 70399 articles. Combine with topic and date filters; results sorted by relevance.
A developer's late September–early October 2026 survey of GPT and Anthropic models found subagent token usage runs 15–35% of a main agent session's usage, and recommends GPT-6 Luna (xhigh) for explore, GPT-6 Luna (high) …
A new tool called Apple Developer MCP lets AI assistants run App Store Connect, builds, releases, and App Store submission end to end, according to its Show HN launch. The agent runs on Nova and can be integrated into Cu…
A new comparison ranks cloud runtime, sandbox and VM compute platforms for AI agents by modeling a monthly bill for one workload scaled from 0.1× to 10× sessions, with concurrency and egress scaling alongside it. The com…
Researchers released DramaAgent, a hierarchical, agentic, model-agnostic framework for long-form text-to-video-and-audio generation, detailed in arXiv paper 2610.00097v1. DramaAgent adds an upper-level control layer that…
Researchers introduced GENSCRIPT, an inference-only synthetic data pipeline that eliminates model training by computing a deterministic statistical profile of source data and passing it to a language model to infer field…
A study posted to arXiv (2610.00313v1) found that scientific coding agents given prepared executable checks completed 29 of 30 repair tasks, versus 26 of 30 when given written requirements alone. In the eight-task-ID coh…
SaharaLabsAI researchers introduced ReLiveGym, a diagnostic evaluation environment that tests long-lived LLM agents over simulated weeks of chronologically replayed real-world news, market, and social-media streams, per …
A developer built an open-source time-travel debugger for AI agents that records execution traces, lets users rewind to earlier states, modify decisions, and replay or branch from any step. The project pairs a Python Age…
A developer building HyperMarrow, a local-first memory layer for agents, catalogued four recurring agent-memory bugs drawn from public issue trackers, including a widely used coding agent where idle compaction silently d…
OpenVoiceOS added a wake word verifier plugin that identifies enrolled household speakers at the wake gate, rejecting television audio and unrecognized voices, as part of a set of updates to the open-source voice assista…
An AI agent's session index silently dropped its final line on 2026-09-23 because the agent's own checker measured the index in characters (24,888) while the loader counted UTF-16 code units (~24,988), pushing it roughly…
Z.ai (Zhipu) has deprecated GLM-4.7, with the model set to retire on 2026-12-31 and be replaced by GLM-5. The glm-4.7 model, which offers a 200k context window and 66k max output, is flagged as retiring soon on the provi…
A new proof establishes that 4k+4 rounds of AES with independent uniform round keys, sampled once and retained across evaluations, have pairwise total variation distance below 2^{-14.3-73.1k} for every integer k≥0, tight…
A developer built an open-source benchmark of 57 bash 3.2 scripts to test whether chat models can predict macOS's 2006-era shell behavior, scoring exit codes and final stdout lines deterministically with no judge LLM. Qw…
Colosseum launched Copilot v2 on October 1, 2026, an upgraded AI agent for Solana developers that now draws on 8,286 projects across five hackathons, including submissions from the recent Frontier Hackathon added to an e…
Cortex Apps released Engrams, an open-source framework for autonomous agent orchestration, according to a GitHub repository, positioning it as an alternative to Cognition's proprietary Devin coding agent. The release is …
IBM announced a self-hosted deployment option for IBM Bob, its agentic software development platform, letting enterprises build and modernize applications on their own infrastructure. The offering supports on-premises, p…
A developer evaluated speculative decoding in vLLM on AMD Instinct MI300X and MI355X GPUs, testing draft methods including MTP, EAGLE-3, DFlash, and DSpark that propose candidate tokens verified in a single forward pass.…
A developer built the Enterprise Multi-Cloud GenAI RAG Platform, an open-source reference implementation that runs locally without paid model APIs and provides equivalent production deployment paths for AWS and Azure, wi…
Factory has made Custom Automations generally available, letting users describe a recurring workflow, choose a schedule or event trigger, and have its Droid agent run it to the intended result with a user-selected model,…