Entity trail

Greptile

Source-backed findings, relationship evidence, citations, and briefing history from the public MindPattern archive.

Briefing refs

Findings

Edges

Sources

Corpus findings

2026-06-09 / skill-finderSplit your review gate: deterministic static analysis for blocking, async AI reviewer for contextual feedbackThe pattern converging across teams in 2026 is to use static analyzers as high-confidence blocking gates (deterministic rules) and run an AI reviewer asynchronously in parallel for semantic, repo-aware feedback that never blocks the pipeline. AI reviewers excel at mechanical bugs and applying a pattern consistently across hundreds of PRs; agentic reviewers like Devin report ~70% auto-fix-on-approval resolution. Wire AI review as a webhook/parallel CI step (CodeRabbit, Greptile, Qodo, Cursor Bugbot) so it surfaces earlier and contextually rather than gating merges on a probabilistic check.
2026-04-01 / sources-researcherGreptile CTO Soohoon Choi: 'Good Code Will Still Win' — Economic Incentives Will Force AI to Stop Writing SlopGreptile co-founder Soohoon Choi published a March 31 essay arguing AI slop is temporary because economics will correct it: good code is cheaper to generate and maintain in tokens, complex code requires exponentially more compute as codebases grow, and LLM providers paid per token are incentivized to optimize for simplicity. Drawing on Ousterhout's software design philosophy, he frames code quality as a market-driven outcome, not an ethical choice. Simon Willison signal-boosted the argument.
2026-04-01 / hn-researcherGreptile: 'Slop Is Not Necessarily the Future' — 261pts, 421 Comments in AI Code Quality DebateGreptile's blog post arguing that markets will not reward AI 'slopware' long-term sparked the highest comment-to-point ratio (1.61) discussion on HN this cycle, with 421 comments on 261 points. The thesis: competition between AI models means the winners will produce simple, maintainable code because good code is cheaper to generate AND maintain. Greptile's own v4 code review tool reports 82% bug catch rate in independent benchmarks — nearly double CodeRabbit (44%) and ahead of GitHub Copilot (54%). The discussion crystallizes the emerging split between 'ship fast with AI' and 'ship right with AI' camps.

Graph relationships

WORKS AT
Soohoon Choi
Soohoon Choi is CTO of Greptile
Source finding
BENCHMARKED AGAINST
GitHub Copilot
Greptile v4 achieves 82% bug catch rate ahead of GitHub Copilot's 54%.
Source finding
BENCHMARKED AGAINST
CodeRabbit
Greptile v4 code review tool reports 82% bug catch rate compared to CodeRabbit's 44%.
Source finding
COMPETES WITH
CodeRabbit
CodeRabbit and Greptile compete as AI review tools.
Source finding
WORKS AT
Soohoon Choi -> Greptile
Soohoon Choi is CTO of Greptile
Source finding

Source trail

Greptile co-founder Soohoon Choi Sourcegraph — Automated Code Review Tools (2026)

Graph sources

entity graphfindings textkg edgeskg entitiesnewsletter issues