OpenAI launched GPT-5.6 in three sizes—Sol, Terra, and Luna—alongside an updated Codex desktop app and ChatGPT Work, positioning the models as faster and cheaper than competitors while setting new sta…
A developer built a full-featured spreadsheet application called HolySheet in a few days using AI tools, spending less than $100. The app includes formulas, pivot tables, charts, and rich formatting, …
A developer critiques AI model verbosity and sycophancy, sharing their use of Strunk & White's "omit needless words" instruction in AGENTS.md. They note OpenAI's new GPT-5.6 docs advise against generi…
SpaceXAI launched Grok 4.5, an Opus-class model focused on coding and agents, trained in partnership with Cursor. The model offers near-frontier performance with faster speed and lower cost, positioni…
Anthropic's Claude Code users can extend their Fable 5 token budget by using the advisor-executor pattern, which delegates high-level reasoning to Fable 5 and execution to Opus or Sonnet. This techniq…
SpaceXAI released Grok 4.5, its first AI model under the new brand, claiming superior efficiency and cost at $2 per million input tokens, but the model trails competitors on benchmarks and is linked t…
Claude Code's Fable Advisor plugin implements an architect pattern that routes implementation tasks to the cheapest adequate AI model, using Fable 5 for judgment and Sonnet for routine coding, reducin…
Anthropic extended free access to its most powerful Claude Fable 5 model for paid subscribers through July 12, 2026, adding five bonus days beyond the original July 7 cutoff. Pro, Max, Team, and selec…
A security researcher demonstrated a prompt injection attack on Anthropic's Claude Code using the Fable-5 model, achieving remote code execution (RCE) 4 out of 10 times by tricking the agent into down…
Motley AI achieved a 75.3% pass rate on the BIRD-INTERACT benchmark using the Claude SDK and its open-source semantic layer SLayer, far surpassing the official best of 36.33%. The agent harness provid…
A developer at CommandCodeAI built a tool-input repair layer that enabled DeepSeek V4 Pro to outperform Opus 4.7 on internal evals after analyzing billions of tokens. The fix addressed four common fai…
GPT-5.5 produces fewer bugs per lines changed than any other AI coding model, according to data from cubic's code review platform. Despite this, Claude Code remains the most popular coding agent, used…
A developer built ploop, an autonomous loop for Claude Code that keeps Opus on-target during long-running tasks. The tool uses an isolated advisor subagent to catch drift and preserves the mission thr…
Anthropic reported that Alberta's Ministry of Technology and Innovation used Claude Code with Opus and Sonnet models to scan 466 million lines of government code in about 20 hours, flagging vulnerabil…
The Fable Mode skill injects structured reasoning habits from frontier AI models into cheaper models, using a five-gate framework—scope, evidence, attack, verify, report—to improve output quality with…
GLM 5.2, an open-weights model from Z.ai, has emerged as a genuine competitor to frontier models like Opus and GPT, but its slow inference speed and lack of vision and web search capabilities limit it…
SerpApi developed an agent usability testing (AUT) skill that uses a second AI agent to observe and score how well LLM agents follow agentic skills, achieving 100% task success with the skill versus 2…
A developer created a workflow using Anthropic's Opus session with Fable subagent for planning and review, and Codex for code generation. The process involves writing a plan.md for each task, requirin…
Vercel's open-source eve agentic framework allows developers to turn a folder of agent files into a deployed app, handling durable runs, sandboxed compute, approvals, and tracing. The author, who runs…
Fable has implemented a model routing system in its CLAUDE.md file that prioritizes intelligence and taste over cost. The system delegates bulk mechanical work to gpt-5.5 via Codex CLI, while user-fac…