Tag
A compiled list of anti-slop tools for coding to reduce AI-generated low-quality code, shared by @juampitech.
Matt Pocock notes that Opus 5 produces high-quality code, with autonomous coding runs still strong, though human-in-the-loop planning has become a nuisance.
The author shares a methodology for building an external LLM drift detection system that continuously probes model behavior (schema adherence, instruction-following, refusal rates, etc.) to catch silent degradations in API performance, and invites feedback on the approach, pricing, and use cases.
A developer reflects on the inevitability of shipping AI features with poor outputs and emphasizes the need for proactive monitoring instead of relying solely on user reports.
Google employees are internally sharing memes criticizing the quality of AI-generated code, contrasting with CEO Sundar Pichai's public statements that 75% of new code is AI-generated.