The Skylight team at the Allen Institute for AI (Ai2) built Shippy, a maritime AI agent for real-time domain awareness, and learned that reliability—not the model—is the core challenge for high-stakes…
Stripe released a benchmark suite evaluating AI agents on end-to-end Stripe integrations, finding that agents struggle with validation and cross-system state tracking despite strong code generation. T…
After twin earthquakes killed more than 3,800 people in northern Venezuela last month, volunteer developers in the diaspora used AI to build websites for disaster relief, including missing-person repo…
Pydantic AI Harness introduces experimental 'loop of agents' features that let an agent delegate tasks to sub-agents and orchestrate them via dynamic workflows, enabling self-structuring, failure isol…
Security expert Thomas Ptacek argues that LLM agents are uniquely suited for vulnerability research, and Anthropic researcher Nicholas Carlini demonstrated that a simple prompt to Claude Opus can iden…
A developer tested the same AI agent (Claude Code with Claude Opus) on four cloud platforms—redu.cloud, AWS, Vercel, and Railway—to deploy a stateful, privacy-first infrastructure stack. redu.cloud an…
A developer created pi-tiered-router, an extension that routes each phase of a coding agent to a different model, optimizing cost and performance. The system breaks a coding turn into classify, plan, …
Z.ai's open-weight model GLM-5.2 is emerging as a cost-effective alternative to proprietary AI code assistants like Opus, offering a million-token context window and advanced features. In testing, it …
AI can teach engineering fundamentals but cannot build the judgment that separates senior engineers from novices. The 'olfact'—an instinct for detecting problems before they occur—comes only from repe…
A developer built Slate-memory, a one-shot attractor memory system that enables the cheap Claude Haiku model to match the accuracy of the expensive Claude Opus model at 1/640th the cost. The system us…
A Hacker News user claims that Anthropic's Claude Opus model has been 'nerfed,' reporting degraded performance and failure to follow instructions over the past week.…
A developer built Model Kombat, a 2D fighting game that visualizes Large Language Model architectures, parameter scales, and hardware constraints as playable mechanics. The game features fighters repr…
A developer proposes replacing LLM API calls with coding agent calls to reduce costs, citing that coding assistants like Codex, Cursor Pro, and GitHub Copilot Pro cost significantly less per million t…
Ploy, an AI agent that builds marketing websites, has migrated its production model from Claude Opus 4.8 to OpenAI's GPT-5.6 Sol after extensive evaluation. The switch resulted in builds finishing in …
A developer built WoW Brain, a neurocognitive OS with 60+ adaptive trainers and an AI Neuro-Probe, using FastAPI, SQLite, and Jinja. The project revealed that real-world cognitive training requires hy…
ClickMinded's 'Little Guys Strike Back' webinar presented a blueprint for building an AI-powered editorial team using agents like Claude Code, Codex, or Cursor. The system assigns different models to …
Elon Musk announced on July 9 that xAI's Grok will receive a 1M+ token context window, matching Anthropic's Claude Opus and intensifying the AI arms race. The upgrade enables processing of roughly 750…
A developer building a personal knowledge system reduced Claude API costs by up to 84% by routing vision OCR tasks to the cheaper Haiku model and concept extraction to Sonnet. The technique separates …
Claude Fable 5 can be used as an orchestrator in multi-agent workflows, delegating execution to cheaper models like Opus or Sonnet, cutting token costs by 10x without quality loss. The approach involv…
SpaceXAI released Grok 4.5, a new AI model that founder Elon Musk described as an 'Opus-class model' comparable to Anthropic's Claude Opus but faster and cheaper. The model costs $2 per million input …