Daily desk

News

Artificial intelligence, technology, science, health and education — reported daily, with the original source attached to every item.

Showing articles about software engineering

6 stories

A failing pre-submit test moves through FlowAgent's propose-and-validate loop and comes out passing, alongside the headline counts of changes flagged, fixes previewed, and fixes applied.
🤖 Artificial Intelligence Study

Google's FlowAgent AI Fixed 28,554 of 295,508 Flagged Pre-Submit Test Failures

Google engineers describe FlowAgent, an AI agent that suggested fixes on 295,508 changes during rollout; developers applied 28,554 of them,…

EduFabTech · 1d ago · 4 min read
A shield with a checkmark represents Gemini 4 Argon patching code flaws, next to its 85.8% vulnerability-discovery score, 68% tied CWE-bench result, and 1M-token context window, with a tag noting it is Fairwind-only for now.
🤖 Artificial Intelligence Report

Google's Gemini 4 Argon Finds and Patches Code Flaws, for Vetted Defenders First

Google DeepMind's Gemini 4 Argon autonomously finds, validates and patches software vulnerabilities, tying GPT-6 Astra and Grok 4.7 on CWE-…

EduFabTech · 4d ago · 4 min read
A schematic shows a support ticket flowing through Clef into calibrated yes/no probabilities, alongside stat tiles on Clef's benchmark wins, latency, and price versus Jev.
🤖 Artificial Intelligence Report

Cloudflare Launches Open-Weight Clef Decision Models, With Self-Reported Wins Over Jev

Cloudflare's new Clef and Clef-flash models answer structured yes/no, multiple-choice and scoring questions for AI agents, undercutting Jev…

EduFabTech · 5d ago · 4 min read
An 11-cell task grid shows GPT-6 Astra (Codex) building 10 of 11 repositories from a spec, the best score in the Zero2Repo benchmark.
🤖 Artificial Intelligence Report

New Zero2Repo Benchmark Finds Top AI Coding Agent Builds 10 of 11 Repositories From a Spec, Weakest Manages Seven

A new benchmark gives AI coding agents a requirements document and an empty folder instead of a bug to patch. The best agent finished 10 of…

EduFabTech · 2 Oct 2026 · 4 min read
A bar comparison shows autonomous coding agents lift commits 240% while releases from the same developers rise only 30%, the paper's "weak-link" gap.
🤖 Artificial Intelligence Study

Autonomous AI Coding Agents Raise Commits 240%, but Software Releases Rise Just 30%, NBER Study Finds

A revised NBER working paper tracking more than 500,000 GitHub developers finds autonomous AI coding agents raise commit activity by 240% b…

EduFabTech · 26 Sep 2026 · 4 min read
🤖 Artificial Intelligence Study

A Verified Version of SWE-Bench Pro Shows Coding Agents Were Reading Answers Off Git History

A new SWE-Bench Pro Verified benchmark closes git-history and web-lookup leaks that let coding agents fetch hidden solutions instead of sol…

EduFabTech · 12 Sep 2026 · 4 min read