An engineer who ran ~$10K/month in Claude Code API bills found that 80% of spending went to frontier models for tasks that didn't need them. By implementing task-level model routing—matching model tie…
A user reports that AI models differ drastically in how long they can run unattended on a host with sudo without causing system issues: Opus breaks hosts within 2 agent-hours, Gemini 3 Pro within 12, …
A study by Cassis on LLM context optimization for data analytics found that adding a full example library raised Haiku's accuracy from 70% to 82% and Sonnet's from 81% to 93%, while removing rules and…
After four attempts and spending $100,000, a team led by an unnamed developer and Jason Seibel succeeded in using Anthropic's Opus AI model to rewrite PostgreSQL in Rust, producing pgrust — 1.8 millio…
After four attempts and spending $100,000, a team led by an unnamed developer succeeded in using Anthropic's Opus to rewrite PostgreSQL in Rust, producing 1.8 million lines of idiomatic Rust code call…
A developer introduced Fable Orchestrator, a multi-agent system that coordinates specialized AI executors—including models like Sonnet, Opus, and Codex gpt-5.6-sol—for software development tasks. The …
A developer has built an open-source system called autoloop that autonomously triages, implements, and tests GitHub issues using Claude AI, achieving 27 autonomous merges in two weeks with a 97% succe…
A user on Hacker News reports that GPT 5.6 Sol is significantly less productive than Opus/Fable, requiring constant steering and producing overreached conclusions and useless defensive code. The user …
A new analysis by AI researcher and open-source harness developer finds that the common practice of using a frontier model to plan and a cheaper model to execute—dubbed the '/plan' pattern—actually in…
EG-VAR, a Lean 4-based architecture for AI reasoning, achieved a flawless 120 out of 120 on TableBench numerical reasoning tasks and maintained 100% source fidelity during counterfactual stress tests,…
A security researcher using Hacktron's pentest tool discovered that PostHog launched Playwright Chromium with `--no-sandbox` for heatmap screenshots, then used Anthropic's Claude to write an exploit f…
OpenAI released GPT-5.6-Sol, alongside cheaper models Terra and Luna, pricing Sol at $5/$30, Terra at $2.50/$15, and Luna at $1/$6. CEO Sam Altman said the models address enterprise cost concerns and …
A developer tracked Claude Code and Codex pass rates for 95 days and calculated the per-session cost of Anthropic's agentic coding tool. A typical mid-size session of 40 model calls with a 90K token w…
A developer has been running an autonomous agent on a 16GB M1 Mac for three months, using small models in the 9B/E4B class by choice rather than economic necessity. The developer argues that small mod…
Anthropic's prompt caching, Batches API, and model routing can significantly reduce LLM costs without switching providers. Prompt caching reuses prefixes at 0.1× the base input price, the Batches API …
A developer created an 'Operating Standard' document that encodes a portable doctrine for AI coding agents, enabling cheaper models like Sonnet and Opus to match the conduct of frontier models without…
A developer shared a starter configuration for Claude Code, a tool that uses AI to assist with coding tasks. The configuration includes a curated allowlist of safe commands, integration with the open-…
An engineer at Anthropic has developed a multi-model playbook for Claude Code, arguing that the biggest leverage comes from loop engineering—designing agentic loops that use cheaper, faster models for…
A developer successfully added Mermaid diagrams to OpenWiki, LangChain's LLM-powered code documentation tool, by modifying its prompts to generate sequence and entity-relationship diagrams. The experi…
A Hacker News user asks the community to share specific tasks from the past month where open-weight models like GLM, DeepSeek, Kimi, or Qwen failed but frontier models like Opus, Fable, or GPT succeed…