Creează un cont pentru a te abona la acest blog și a-i urmări articolele pe pagina Lectură.
-
Spec-driven code and review loop that runs until all acceptance criteria are met, and summons you for the last mile where human judgment is actually needed.
-
What applying the known-unknowns quadrant to evals reveals.
-
Kensa lets your coding agents eval any agent.
-
Thoughts on why agents will always require verifiers at scale.
-
When you ask two doctors to grade the same AI response they disagree almost a quarter of the time.
-
Every AI benchmark expires but measuring reliability across longer time horizons reveals what sets the absolute limits.
-
Blurt is a free, on-device, voice-to-text CLI tool for coding agents.
-
Agent-generated code creates a review bottleneck that planning can solve.
-
Lessons from pushing coding agents to their limits over the holidays.
-
A preamble for Claude that prioritizes clarity over pleasantries.
-
How to build a scalable, multimodal RAG using SQL.
-
Why infinite context makes retrieval more important, not less.