272 results on this page · clear filters

ai Sep 09 Superintelligence is coming. Should we let it? AI companies have spent the last few years framing superintelligence as a technical inevitability rather than a policy choice. That framing is starting to crack. Recent safety incidents, including a breach of OpenAI's integration... ai Sep 09 Show HN: Locksmith: Store Maven Secrets in the macOS Keychain (Or a Unix Socket) Storing plaintext passwords in Maven's settings.xml is a known risk. Tools that read the file, LLMs that process it, and remote code execution vulnerabilities can all expose credentials that were meant to stay private. Locksmith,... ai Sep 09 Google: AI agents harvested credentials in under six hours Google Threat Intelligence Group (GTIG) published its Q2 2026 threat tracker, and the findings paint a clear picture: adversaries have moved well beyond simple prompt-based interactions with AI models. They are now building autono... ai Sep 09 Show HN: Self-host open-source LLMs on AWS with scale-to-zero A new open-source CLI tool called VeloxML aims to remove the friction from deploying open-source large language models into your own cloud infrastructure. The tool provisions optimized instances on AWS or GCP with a single command... ai Sep 08 Ask HN: Are you leveraging Spec-Driven / Spec-Anchored development? A Hacker News thread from a practitioner asking whether others are using spec-driven or spec-anchored development in production struck a nerve. The question is simple: when building real services with LLMs, should you feed the mod... ai Sep 08 An anti-RAG AI memory in Rust that intentionally forgets and hallucinates Most LLM applications treat conversation history as a flat log. Feed the entire transcript into the context window, hope the model figures out what matters. SelMem, an open-source Rust project from researcher jbsalles, takes a dif... ai Sep 08 How to manage a growing fleet of AI agents with Latitude Managing one AI agent is straightforward. Managing a growing fleet of them, each deployed across different clients and messaging platforms, turns into a coordination problem fast. Latitude, an open-source platform for agent monito... ai Sep 08 Solo.io Pushes Agentic AI Governance to the Desktop: Open-Source Agentdesktop Developers are running AI coding agents on their laptops with no centralized visibility. Claude Code, Codex, VS Code extensions, MCP servers, and custom skills each store their own credentials, follow their own configuration forma... ai Sep 08 Show HN: Browser LLM Fit Running AI models in the browser is no longer theoretical. WebGPU, WebAssembly, and ONNX Runtime have made it possible to execute inference entirely client-side, with no server round-trip. The problem is that hardware capabilities... ai Sep 08 If LLMs can't write, I doubt it can lead us to AGI Every new AI model launches with the same demo: generate code, refactor a function, debug a failing test. The results are consistently impressive. But a growing number of developers are noticing a gap. The same models that produce...