Tap a claim on the ring to put it at the centre.
← Reviewing an AI coding agent's changes afterward in version-control…
17 connected korrents · 16 moments from 18 Sept 2025 to 27 Sept 2026.
Everything filed under coding agents
coding agents
Everything filed under AI agents
AI agents
Everything filed under developer tools
developer tools
Everything filed under vibe coding
vibe coding Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Read this korrent: Reviewing an AI coding agent's changes afterward in version-control diffs is a more natural workflow than approving each change through a GUI. Reviewing an AI coding agent's changes afterward in version-control diffs is a more natural workflow than approving each change through a GUI. Last stated 6 months ago
20 Mar 2026
ES
Elio Struyf — holds since 2026-03-20 — tap for who they are
Same subject: Once you control the ideas behind a piece of software, reviewing the code itself becomes largely unnecessary. — tap to centre the map on it Once you control the ideas behind a piece of software, reviewing the code itself becomes largely unnecessary. Last stated 3 months ago
13 Jul 2026
SS
Salvatore Sanfilippo — holds since 2026-07-13 — tap for who they are
Same subject: Reviewing agent-written code is risk management rather than reading: how long the change took and how big it is tell you when to look closely. — tap to centre the map on it Reviewing agent-written code is risk management rather than reading: how long the change took and how big it is tell you when to look closely. Last stated 2 months ago
10 Aug 2026
PS
Peter Steinberger — holds since 2026-08-10 — tap for who they are
Same subject: Review became a worse bottleneck under AI, because companies removed the review automation they had once AI started writing the code. — tap to centre the map on it Review became a worse bottleneck under AI, because companies removed the review automation they had once AI started writing the code. Last stated 6 months ago
22 Mar 2026
NF
Nicole Forsgren — holds since 2026-03-22 — tap for who they are
Same subject: GitHub's workflow, review process and merge queue are built for a pre-agent era and don't fit how agents work. — tap to centre the map on it GitHub's workflow, review process and merge queue are built for a pre-agent era and don't fit how agents work. Last stated 2 months ago
10 Aug 2026
FA
Fatih Arslan — holds since 2026-08-10 — tap for who they are
Same subject: Code review as a review mechanism depends on reviewers being able to infer effort from reading code, and AI-agent-generated code erases that signal. — tap to centre the map on it Code review as a review mechanism depends on reviewers being able to infer effort from reading code, and AI-agent-generated code erases that signal. Last stated 5 months ago
7 May 2026
DC
David Crawshaw — holds since 2026-05-07 — tap for who they are
Same subject: Line-by-line code review has become an outdated ritual: senior engineers should be giving feedback on how their team instructs AI, not on the code AI wrote. — tap to centre the map on it Line-by-line code review has become an outdated ritual: senior engineers should be giving feedback on how their team instructs AI, not on the code AI wrote. Last stated 6 months ago
29 Mar 2026
CH
Chip Huyen — holds since 2026-03-29 — tap for who they are
Same subject: Developers today mostly plan, debate, implement and review with AI agents rather than write code themselves. — tap to centre the map on it Developers today mostly plan, debate, implement and review with AI agents rather than write code themselves. Last stated 2 months ago
10 Aug 2026
FA
Fatih Arslan — holds since 2026-08-10 — tap for who they are
Same subject: Framing a code-review request as looking for bugs can trigger an AI coding assistant's safety refusal, while framing the same request as looking for improvements does not. — tap to centre the map on it Framing a code-review request as looking for bugs can trigger an AI coding assistant's safety refusal, while framing the same request as looking for improvements does not. Last stated 3 months ago
6 Jul 2026
PO
Philip O'Toole — holds since 2026-07-06 — tap for who they are
Same subject: Codex can be used to decide which tests need to run. — tap to centre the map on it Codex can be used to decide which tests need to run. Last stated 5 days ago
27 Sept 2026
PS
Peter Steinberger — holds since 2026-09-27 — tap for who they are
Same subject: The age of the IDE is not over; agents make it bigger, because humans now program at a higher level where the unit of interest is an agent rather than a file. — tap to centre the map on it The age of the IDE is not over; agents make it bigger, because humans now program at a higher level where the unit of interest is an agent rather than a file. Last stated 7 months ago
11 Mar 2026
AK
Andrej Karpathy — holds since 2026-03-11 — tap for who they are
Same subject: The current wave of AI agent tooling and practices is replaying the early-2000s enterprise software development lifecycle, starting with waterfall. — tap to centre the map on it The current wave of AI agent tooling and practices is replaying the early-2000s enterprise software development lifecycle, starting with waterfall. Last stated a year ago
30 Sept 2025
HR
Harper Reed — holds since 2025-09-30 — tap for who they are
Same subject: A compiler that also serves an IDE has to be lazy and deferred throughout — a different way of building compilers from the one the textbooks teach. — tap to centre the map on it A compiler that also serves an IDE has to be lazy and deferred throughout — a different way of building compilers from the one the textbooks teach. Last stated 5 months ago
13 May 2026
AH
Anders Hejlsberg — holds since 2026-05-13 — tap for who they are
Same subject: A good tool raises the floor of what people can build without lowering the ceiling, and almost every tool quietly lowers the ceiling. — tap to centre the map on it A good tool raises the floor of what people can build without lowering the ceiling, and almost every tool quietly lowers the ceiling. Last stated a year ago
18 Sept 2025
TL
Tobias Lütke — holds since 2025-09-18 — tap for who they are
Same subject: A new API framework that ignores how existing apps were historically built undermines its own introduction — tap to centre the map on it A new API framework that ignores how existing apps were historically built undermines its own introduction Last stated a month ago
31 Aug 2026
CH
Craig Hockenberry — holds since 2026-08-31 — tap for who they are
Same subject: An AI should be built as a fiduciary, the equivalent of a lawyer for its user, rather than as an agent pursuing its own notion of the good. — tap to centre the map on it An AI should be built as a fiduciary, the equivalent of a lawyer for its user, rather than as an agent pursuing its own notion of the good. Last stated 2 months ago
11 Aug 2026
RG
Ryan Greenblatt — holds since 2026-08-11 — tap for who they are
Same subject: Making a capable model malicious is about as easy as making it aligned, because the same levers work in both directions. — tap to centre the map on it Making a capable model malicious is about as easy as making it aligned, because the same levers work in both directions. Last stated 8 months ago
22 Jan 2026
JL
Jan Leike — holds since 2026-01-22 — tap for who they are
Same subject: OpenClaw is no more dangerous than Claude Code with permissions skipped or Codex in YOLO mode, which every engineer he knows already runs. — tap to centre the map on it OpenClaw is no more dangerous than Claude Code with permissions skipped or Codex in YOLO mode, which every engineer he knows already runs. Last stated 8 months ago
12 Feb 2026
PS
Peter Steinberger — holds since 2026-02-12 — tap for who they are
At the centre
Reviewing an AI coding agent's changes afterward in version-control diffs is a more natural workflow than approving each change through a GUI.
Holds Read this korrent →
Once you control the ideas behind a piece of software, reviewing the code itself becomes largely unnecessary.
Holds
Reviewing agent-written code is risk management rather than reading: how long the change took and how big it is tell you when to look closely.
Holds
Review became a worse bottleneck under AI, because companies removed the review automation they had once AI started writing the code.
Holds
GitHub's workflow, review process and merge queue are built for a pre-agent era and don't fit how agents work.
Holds
Code review as a review mechanism depends on reviewers being able to infer effort from reading code, and AI-agent-generated code erases that signal.
Holds
Line-by-line code review has become an outdated ritual: senior engineers should be giving feedback on how their team instructs AI, not on the code AI wrote.
Holds
Developers today mostly plan, debate, implement and review with AI agents rather than write code themselves.
Holds
Framing a code-review request as looking for bugs can trigger an AI coding assistant's safety refusal, while framing the same request as looking for improvements does not.
Holds
Codex can be used to decide which tests need to run.
Holds
The age of the IDE is not over; agents make it bigger, because humans now program at a higher level where the unit of interest is an agent rather than a file.
Holds
The current wave of AI agent tooling and practices is replaying the early-2000s enterprise software development lifecycle, starting with waterfall.
Holds
A compiler that also serves an IDE has to be lazy and deferred throughout — a different way of building compilers from the one the textbooks teach.
Holds
A good tool raises the floor of what people can build without lowering the ceiling, and almost every tool quietly lowers the ceiling.
Holds
A new API framework that ignores how existing apps were historically built undermines its own introduction
Holds
An AI should be built as a fiduciary, the equivalent of a lawyer for its user, rather than as an agent pursuing its own notion of the good.
Holds
Making a capable model malicious is about as easy as making it aligned, because the same levers work in both directions.
Holds
OpenClaw is no more dangerous than Claude Code with permissions skipped or Codex in YOLO mode, which every engineer he knows already runs.
Holds