Machine Learning SWE-Together: Grade Coding Agents on Multi-Turn Sessions
Build a SWE-Together-style multi-turn coding-agent eval with an LLM user simulator in Python.
How-to content for builders, indie hackers, and AI engineers. Less theory, more shipped code.
Machine Learning Build a SWE-Together-style multi-turn coding-agent eval with an LLM user simulator in Python.
Tutorials Use Anthropic's compact-2026-01-12 beta so long agentic loops survive past the 200K context window.
Tutorials Load SKILL.md files into a Claude Agent SDK app with setting_sources and the skills option.
Tutorials Meituan's 1.6T open MoE topped OpenRouter as 'Owl Alpha.' Call it in Python with the OpenAI SDK.
Tutorials Give Claude agents a token countdown so long agentic loops finish gracefully instead of burning your bill.
Tutorials Build cheap, cited research agents on Claude Sonnet 5 using the web search tool and dynamic filtering.
Tutorials Stand up an autonomous agent with sessions, streaming events, and webhooks - no agent loop required.
Tutorials Sonnet 5 claims better hijack resistance. Here's how to measure it yourself.
Tutorials Master Sonnet 5's on-by-default thinking and the effort knob to cut cost and latency.
Tutorials Hands-on Python guide to Sonnet 5's adaptive thinking, effort levels, and the 30% tokenizer trap.
Tutorials Enable Claude Code's experimental Agent Teams: peer messaging and a self-claiming shared task list.
Tutorials Cut MCP agent context up to 99% by exposing tools as a code API the model calls in code.