Karpathy declares agentic engineering next coding evolution

// 1h agoNEWS

Karpathy declares agentic engineering next coding evolution

In a shared post on X, AI pioneer Andrej Karpathy highlights a shift in software engineering paradigms, stating that while vibe coding has been a popular starting point, agentic engineering represents the next level of development. Karpathy notes that approximately 90% of his own coding routine is now automated through these agentic workflows, underscoring the rapid transition from manual code generation to orchestrating autonomous AI agents in software development.

// ANALYSIS

Agentic engineering is transitioning from a developer trend to the standard operating procedure for modern software development.

* Paradigm Shift: Developers are moving away from ad-hoc prompt engineering ("vibe coding") toward designing, orchestrating, and monitoring complex autonomous agent systems.

* Automation Level: Karpathy's claim that 90% of his coding is automated highlights how quickly high-level logic and agent orchestration are replacing manual coding.

* Skill Revaluation: The core value of a software engineer is rapidly shifting from syntax writing to system architecture, testing, and agent management.

// TAGS

ai-codingagentic-engineeringsoftware-engineeringartificial-intelligenceandrej-karpathydeveloper-productivity

DISCOVERED

1h ago

2026-06-08

PUBLISHED

2h ago

2026-06-08

RELEVANCE

8/ 10

AUTHOR

Av1dlive

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

VIDEO39m ago

Mastra outlines transition to structured specifications

In this episode of the AI Agents Hour, Mastra co-founders Shane Thomas and Abhi Aiyer explore shifting from manual prompting to structured, developer-first agent specifications. The discussion covers tool integrations like CodeRabbit for pull request reviews and Freestyle's forkable Linux VM sandboxes to build reliable, deterministic AI agents.

BENCHMARK58m ago

Cognition has introduced FrontierCode, a software engineering benchmark that measures the mergeability, quality, and maintainability of AI-generated code rather than simple functional correctness.

Cognition has launched FrontierCode, a new software engineering benchmark designed to evaluate whether AI-generated code meets the high standards of production-grade codebases. Developed in partnership with the maintainers of 36 flagship open-source repositories who spent over 40 hours per task, the benchmark consists of three nested subsets (Extended, Main, and Diamond) totaling 150 tasks. FrontierCode goes beyond classical unit tests to measure mergeability, style, regression safety, and scope using novel grading methods like reverse-classical testing (which ensures agent-written tests fail on the buggy base code) and adaptive classical grading with their new tool, mutagent. In initial testing, Claude Opus 4.8 led all models but only scored 13.4% on the hardest Diamond set, highlighting that frontier models still struggle significantly with writing production-ready, maintainable code.

MODEL1h ago

Claude Mythos is rumored to launch within the next two weeks, reportedly outperforming Opus 4.8 in coding and reasoning.

According to a post by BridgeMind AI on X, Anthropic's Claude Mythos model is set to release this week or next. In head-to-head comparisons with Opus 4.8, Mythos reportedly wins in almost every category, demonstrating extreme capabilities as a coding and reasoning model.