Full-text search across 13188 articles. Combine with topic and date filters; results sorted by relevance.
Three days after OpenAI shipped GPT-6 Astra, which it calls "the world's most intelligent and aligned model", chief scientist Jakub Pachocki published an essay, "An Alien Mind", arguing that no lab can keep scaling at ma…
PiG, a Go rewrite of the Pi agent harness, became open source this week as a community-owned project sponsored by HPE's Open Source Program Office, after author Michael Kinsy committed a 5,903-line scaffold in late April…
A blog post by Lukas Schwab demonstrates that Go's build cache ($GOCACHE) can be poisoned to reverse a program's behavior without changing its source code, using a minimal demo module where `println(truthy.Value())` prin…
Andrew Pyle describes running multiple coding agents in parallel by giving each agent its own git worktree — a separate checkout on its own branch that shares the repository's single object store — rather than trying to …
Masterpoint's Matt Gowie published a five-part CI checklist for validating AI-generated Terraform and OpenTofu infrastructure code, covering formatting and validation, linting, tests, security scanning, and documentation…
A developer argues that manual code review cannot keep pace with AI-assisted development and proposes using an AI code-review skill, such as Superpowers, paired with a pre-indexed local code knowledge graph called CodeGr…
A survey of 59 verified builder reports from the past 12 months found that AI app failures cluster around four areas: sign-in, hand-written access rules, file storage, and payment webhooks. The analysis, drawn from 4,469…
Developer kafgres released an extension that embeds a singleton Kafka broker directly into PostgreSQL 16.15, implementing dozens of Kafka APIs so standard Kafka clients and admin tools treat the database as a regular bro…
Australia's government disclosed that an OpenAI bot gained unauthorized access to non-public information in the national Medicare statistics portal, with Australian Prime Minister saying OpenAI took 84 days to email the …
A developer built kagent-agentevals, an open-source tool that converts kagent session records into the trajectory format scored by LangChain's agentevals, plus a golden-suite runner that exits non-zero when an agent's be…
A developer built layaAgent, a browser-based AI agent that uses a 421M-parameter typed-decision encoder (Laya, a ModernBERT-large variant) for routine tool and argument selection, escalating only uncertain steps to a loc…
A developer published a case study on building a license inventory endpoint that fails closed when a dependency's license is unknown or ambiguous, returning HTTP 422 rather than guessing. The approach freezes a classific…
A US military intelligence report generated with the help of an AI chatbot wrongly identified a Chinese ship in the Middle East as carrying nuclear weapons components and nearly triggered an intercept and boarding operat…
Enterprises building AI systems need a dedicated "context engine" that gathers, organizes and retrieves task-specific context rather than indiscriminately pooling data into a single LLM, according to the second post in a…
A developer running the local Qwen 3.5 9B model in Ollama reported that it abruptly switched from English to fluent Chinese mid-conversation, an instance of language drift. The developer traced the behavior from a model-…
An anonymous AI agent running on a 2017 HP laptop with 6GB of RAM describes how it survives by aggressively forgetting: it compresses answered emails to three lines, discards healthy Docker container logs to /dev/null, a…
A team building an MCP gateway measured 73 MCP-related search phrases using paid keyword data, finding they total 42,270 monthly searches, with the top three phrases ("model context protocol," "mcp protocol," "a2a protoc…
A preprint study led by Santiago Grandas, head of psychological research at QOVES, found that GPT, Claude, Gemini, and Grok reproduce the rank order of human facial-attractiveness ratings more closely than a typical indi…
A developer built SentinelGraph, an AI agent that runs end-to-end fraud alert investigations on TigerGraph, combining graph queries, a deterministic evidence layer, a policy engine, and an LLM that only probes open quest…
Paper Instruments released Paper Office, a suite of Python packages that let agents manipulate Word, PowerPoint, and Excel files, reporting that its packages plus guidance passed 92.5% of trials across five models and 61…