AIQB
TutorialsOrdinary

Agents tripled commits, but releases only rose 30%: 6 places the extra code piles up before it ships in 2026

Source: DEV Community·

Summary

NBER: autonomous coding agents raised commits 240%, but releases rose only 30%. Six places the extra code waits before it ships, from rewrites to releases.
CategoryAI Tutorials & Practice
TierOrdinary
Published
Indexed by AIQB
SourceDEV Community
AIQB record IDintel-a0c826d5350bd8e23d951cb1
Read original source ↗More Tutorials

Related stories

Matched by category, entity tags and source

TutorialsOrdinary
Keep a 50% Margin on an AI Subscription: Per-User Cost Caps That Actually Bind
If you sell a monthly plan that talks to large language models, the user who loves the product is the...
Source: DEV Community
TutorialsOrdinary
How an 8MB MCP Tool Response Crashes Claude Code — And How to Debug Prompt Cache Misses Across Agents
If you use Claude Code, OpenAI Codex CLI, Cursor, or VS Code Copilot with Model Context Protocol...
Source: DEV Community · OpenAI / Claude / Cursor
TutorialsOrdinary
One Month After the Hackathon: Why My 4-Service App Stopped Working (and What @mansio Caught in the Verifiers)
What breaks a month after a hackathon, and what a fellow DEV writer caught in the verifiers. TL;DR:...
Source: DEV Community
TutorialsOrdinary
Can't Beat Free: Gemma 4 31B on AMD Token Lab, with a Local Chat Page and an ADK Agent
AMD Token Lab is a free OpenAI-compatible API on AMD GPUs that comes with the AMD AI Developer Program. How to sign up, a local chat page that keeps the key off the browser, a terminal client, and a small ADK agent that calls Gemma 4 31B t…
Source: DEV Community · OpenAI
TutorialsOrdinary
Restricting MCP connectors to read-only access
Say you're building a platform where agents read Jira. You could write a Jira client and a set of...
Source: DEV Community
TutorialsOrdinary
We tested 37,000 MCP servers. Here's how many actually work
We connected to every remote server in the official MCP registry the way an MCP client does. 9 in 10 answered, 1 in 3 wants a key before it shows its tools, and 12% of the registry turned out to be spam. Here is the data and what it means …
Source: DEV Community
TutorialsOrdinary
Congrats to the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine Winners!
The results are in for the final week of our Hacktoberfest DEV Challenges! For Ghost in the Machine,...
Source: DEV Community
TutorialsOrdinary
AI Didn't Invent Cybercrime. It Made It Faster, Cheaper, and Harder to Defend.
A source-led investigation of the major AI-enabled cyber incidents of 2024–25 — autonomous espionage, deepfake fraud, operational malware. What the evidence proves, what's hype, and which defenses still work.
Source: DEV Community
TutorialsOrdinary
My Second Dance with Hacktoberfest (2026)
It all started with a sticker. Two years ago, I saw an MLH sticker on a friend's laptop 💻, looked up...
Source: DEV Community
TutorialsOrdinary
AI-Native SDLC in Practice: Anthropic's Playbook, Spec-Driven Development and AWS AI-DLC
Hi Folks! Are you all right? everything in peace? Everything calm? I hope you are well! It's been a...
Source: DEV Community · Claude