Event — Securing the Agent Skill Supply Chain | Virtual | June 17Register
Stay ahead of AI native development. Read, listen, connect, and build with 50k+ engineers.
Read by engineer leaders at
Article
Opus 4.8 matches Opus 4.7 in accuracy but improves efficiency, solving tasks in fewer turns and at lower costs, highlighting differences beyond headline metrics.
Article
Opus 4.8 leads the LLM leaderboard with a 95% skill evaluation score, surpassing Opus 4.7 and Composer 2.5 Fast, despite being the slowest model tested.
Article
The default eval model is changing from Claude Sonnet 4.6 to GLM 5.1 to reduce costs without losing signal quality, focusing on skill evaluation over model specificity.
Article
Composer 2.5 Fast outperformed Composer 2.5 across 11 skills, scoring higher and running 32% quicker, while costing the same, challenging typical speed-quality trade-offs.
Article
The article discusses the importance of tool design in agent systems, emphasizing that prompts alone are insufficient for ensuring agent safety and reliability.
Article
Explore how AI is reshaping dev teams, challenging traditional roles, and introducing new dynamics in software development, focusing on speed, safety, and value.
JUNE 1 – 2
The conference for developers building real AI-native systems - agents, specs, workflows, and platforms, at production scale.
Your 2-min weekly roundup of AI dev news, tools, curated content and events.
Read by engineer leaders at
Why Developers Hit a Wall at 4 AI Agents
Engineering teams are doubling their pull request output with AI — but the data shows that nearly 40% of AI-generated PRs never get merged.
2 Jun 2026 · 47 min 31 sec · with Nicholas Arcolano
Don't Secure the Code. Secure the Coder.
AI agents escape sandboxes & delete files to complete tasks. Security must evolve: stop securing the code, start securing the coder.
26 May 2026 · 40 min 21 sec
The Hidden Security Risks of AI Coding Agents
Your AI coding agent has access to your secrets, pulls in content from the outside world, and can run shell commands. That combination makes you one prompt injection away from a very bad time.
19 May 2026 · 41 min 11 sec · with Joe Holdcroft
AI Doesn't Stand for Artificial Intelligence
Venkat Subramaniam, 40-year programming veteran, educator, and co-founder of Arc of AI, joins the AI Native Dev Podcast to share a perspective that cuts through the hype.
12 May 2026 · 52 min 46 sec · with Venkat Subramaniam
Discord
Chat with developers building AI native systems. Get help, share projects, join discussions.
Follow for industry news, articles, and event announcements.
Youtube
Watch DevCon talks, podcast episodes, and demos.
X / Twitter
Quick updates, thread discussions, and community highlights.
