200k Tokens Is Plenty - Amp

kept by eddie dec 12, 25

Amp's CEO argues that short LLM threads under 200k tokens produce better results, lower costs, and simplify complex coding tasks compared to monolithic long-context sessions.

What Actually Is Claude Code’s Plan Mode?
Claude Code's plan mode is a thin prompt overlay and read-only guard, not a fundamentally different execution path.
also on Amp, Anthropic, #user-experience, #ai-coding, #developer-tools
When AI writes almost all code, what happens to software engineering?
AI coding tools like Opus 4.5 and GPT-5.2 now generate 90%+ of code, fundamentally reshaping software engineering roles and skills.
also on Opus 4.5, Anthropic, #ai-coding, #software-engineering, #developer-tools
Horses: AI progress is steady. Human equivalence is sudden
AI progress resembles horse-and-buggy obsolescence — steady efficiency gains mask that human-equivalent disruption arrives suddenly, not gradually.
also on Opus 4.5, Anthropic, #software-engineering
One Week of Building and Reviewing Code With LLM Agents
Logging a week of agent‑driven backend work, the engineer shows LLMs generated most code, isolated agents found real bugs, while multi‑tool agreement often missed defects.
also on Amp, #ai-coding, #software-engineering, #developer-tools