Large language model (LLM) news — GPT-4, Claude, Gemini, Llama, Mistral and the latest research on training, fine-tuning, RLHF, and deployment of LLMs.
A developer at dualform labs released two open-source skills for Claude Code that address common agent failures: spec, which forces upfront clarification of ambiguous tasks, and review-audit, which performs a read-only a…
A developer refactored a 900-line demonstration file into a reusable Python package called 'harness', which includes modules for action registration, permission budgeting, input sanitization, audit logging, and rollback …
A developer reports that AI is transforming production debugging by rapidly reading and correlating heterogeneous signals, with tools like Datadog's Bits AI SRE claiming time-to-resolution wins of up to 95% in benchmarke…
ScopeKit launched a new tool that creates task-specific context packs for AI coding agents, providing relevant files, symbols, tests, and relationships for a given task. The tool claims to reduce context size by up to 94…
Nylas introduces Agent Accounts with a human-in-the-loop email approval workflow that uses a drafts folder as a safety gate. The system allows an LLM to draft replies automatically while high-risk messages are held for h…
Anthropic disabled access to its advanced AI models, including Mythos, after the Trump administration ordered the company to block foreign nationals from using the technology, citing national security. The unprecedented …
A developer argues that most RAG applications fail because they still parse PDFs as plain text instead of preserving document layout. The recommended approach is to use tools that output structured Markdown, such as IBM'…
A developer identifies four failure vectors that cause LLM prompts to break in production: input distribution mismatch, context contamination over multi-turn conversations, model drift from provider updates, and adversar…
Microsoft released Intelligent Terminal for Windows 11, a fork of Windows Terminal that adds an AI-powered side panel for command-line assistance. The tool supports GitHub Copilot and other Agent Client Protocol-compatib…
SK Group Chairman Chey Tae-won urged employees to adopt AI agents as part of a companywide AI transformation, calling for a "one-person, one-agent" initiative at the 2026 Icheon Forum. Chey said more than 90% of employee…
OpenAI's Codex now completes 85-90% of well-scoped maintenance tasks using its /goal workflow, which loops until a goal is verified complete or a token budget is exhausted. The feature, available in Codex CLI 0.128.0 and…
A cloud architect at an unnamed company reduced their recommendation engine's AI spend by 60% without sacrificing quality by switching from a single-model architecture to a tiered routing system. The team now uses cheape…
A developer built a 'Grovel Index' to measure sycophancy in LLMs, spending ~1.2M tokens testing DeepSeek and Claude models. The key finding is that sycophancy is scenario-specific, not model-specific, with each model faw…
Via v0.4.0 introduces a CLI prompt engine that learns from a developer's codebase history, improving prompts over time by storing successful patterns and past failures. Inspired by the MemAPO research paper, the tool run…
A developer built ccglass, a local loopback reverse proxy for coding agents, after finding that SaaS AI observability tools like Langfuse and Helicone do not work with native CLIs such as Claude Code and Codex. The proxy…
A Hacker News user asks which cheap Chinese large language models the community is using, citing recent releases like DeepSeek V4 Pro, Mimo V2.5 Pro, MiniMax M3, and GLM 5.2, and invites discussion on their performance, …
Anthropic's Claude overtook Google's Gemini to become the second-highest-grossing generative AI app on Apple's App Store in South Korea, challenging the dominance of ChatGPT and Gemini. Claude surpassed Gemini on March 2…
A developer building a tutoring AI initially used vector RAG to retrieve similar past problems, but the approach performed poorly. After investigating, they found that semantic similarity did not equate to the needed sol…
Anthropic suspended access to its Fable 5 and Mythos 5 AI models after receiving a U.S. government directive citing national security concerns, including potential jailbreaking that could aid hacking. The order, reported…
A developer cut RAG costs by 65% by switching from GPT-4o to DeepSeek models with ChromaDB, based on benchmarks of 184 models. DeepSeek V4 Pro outperformed GPT-4o in quality scores while costing a fraction of the price. …