Stanford Researchers Release OpenJarvis | Garry Tan Releases gstack Here is your today’s AI Dev Brief from Marktechpost, covering core research, models, infrastructure tools, and applied updates for AI developers and … https://www.aidevsignals.com/p/stanford-researchers-release-openjarvis-garry-tan-releases-gstack?utm_source=flipboard&utm_content=fluentai%2Fmagazine%2FAIdeas #Technology #Learning #StanfordU #CodeReviews
Stanford Researchers Release OpenJarvis | Garry Tan Releases gstack

AI Dev News (Marktechpost.com)
Qodo's #AI apparently "outshines" #Claude in code reviews, but you'd need a PhD in #jargon to figure out how. 🤖✨ Instead of book reviews, maybe they should book a course in #brevity. 🧠💼
https://www.qodo.ai/blog/qodo-outperforms-claude-in-code-review-benchmark/ #Qodo #CodeReviews #HackerNews #ngated
Qodo Outperforms Claude in Code Review Benchmark

Our latest benchmark reveals Qodo surpasses Claude Code Review in AI code review performance. Read more in the blog.

Qodo
🚨 Breaking News: In a shocking revelation, countless PRs from the elite SWE-bench-passers are deemed unworthy of the sacred 'Merge' button. 🤯 Apparently, the real challenge isn't passing the bench... it's convincing Parker, Cheryl, and Joel that your code isn't as useful as a screen door on a submarine. 🚪🛳️
https://metr.org/notes/2026-03-10-many-swe-bench-passing-prs-would-not-be-merged-into-main/ #BreakingNews #SWEbenchPassers #CodeReviews #MergeButton #DeveloperChallenges #HackerNews #ngated
Many SWE-bench-Passing PRs Would Not Be Merged into Main

Git is the new code

AI is writing more code than ever before (if not all of it). But our most important job as developers hasn’t gone away—it’s simply changed. We spend less time typing code and more time reading, reviewing, and making sure everything works as it should. Here are some quick guidelines and git commands to help you

Neciu Dan

If Code Is Cheap, Intent Is the Currency, by (not on Mastodon or Bluesky):

https://zknill.io/posts/commit-message-intent/

#aiagents #ai #codereviews #documentation

If code is cheap, intent is the currency — /dev/knill

Generating code is cheap now, so the intent behind it matters more than ever. The commit message is where that intent lives.

/dev/knill
How We Do Code Reviews at Cloud Four

If your team members dread the notification that they’ve been added as a reviewer on a pull request, I think the following guidelines can help.

Cloud Four

#Development #Analyses
How to kill the code review · What if no one has to read the code at all? https://ilo.im/16b2il

_____
#AI #Engineering #Coding #CodeReviews #CognitiveDebt #Specifications #Trust #WebDev #Frontend #Backend

How to Kill the Code Review

Human-written code died in 2025. Code reviews will die in 2026.

Latent.Space

#Development #Analyses
The consensus of the AI coding debate · “The work moved, it didn’t disappear.” https://ilo.im/16arom

_____
#Business #Programming #Coding #CodeReviews #AI #Agents #Productivity #WebDev #Frontend #Backend

The Work Moved: What the AI Coding Debate Actually Agrees On

AI agents generate 98% more PRs but reviews take 91% longer. The work didn't disappear — it moved. A synthesis of eight perspectives on where it actually went.

Leadership Garden

erk, i messed up the args to openssl, so rather than encrypting something with a password from a file called .pass, it used the literal string ".pass".

It only took ~6 months to spot.

#sigh #CodeReviews

Building GitHuman: An AI-Coded Tool for Reviewing AI Code

Like everyone else, I had to build something over the end-of-year break. I wanted to fix a burning problem I had: how could I review the code my agents...

Adventures in Nodeland