Overdrivr
Re:Harvard researchers find AI coding agents shifted the bottleneck to...
on Wednesday November 18, 2026 @12:26AM (#50542216)
IMO it's mostly a matter of changing how we do code reviews. I focus on API interfaces, database schema changes, critical code paths (transactions, potential locks) and overall architecture because if we get those right, if the code isn't exactly how I would have thought, it's fine (including in production). And you can review most of this stuff by skimming through the code rather than doing a very thorough review of every line
Re:Jonathan Blow – If AI Solved Coding, Why Is My Software Still the S...
on Saturday November 14, 2026 @01:12AM (#50494492)
It's because the hard part of making software is not coding, but deciding what's worth building (even with LLMs), appropriately modelling the problem and designing the solution (at a conceptual, architectural level). And there has been strictly zero progress on this and IMO this isn't something LLMs are strucurally capable of doing.
Re:Show HN: An open-source manufacturing ERP/MES/QMS
on Thursday September 24, 2026 @12:07AM (#49826134)
How do you handle the challenge of getting self-hosted customers to upgrade? I'm guessing a lot of self-hosted instances end up running fairly customized versions of your product.
Disclaimer: I'm the founder of Bonx (bonx.com). Genuinely curious — congrats on what you've built, and best of luck!
Re:Claudette: Make Claude Stop Talking Like a BuzzFeed Article
on Saturday August 22, 2026 @04:32PM (#49403600)
Just telling claude to speak in simplified technical english really helped quite a lot. It even wrote one liners as PR description for minor bugfixes, something that never happened before I used that trick
Re:Show HN: How far you can go with an electric car
on Thursday April 14, 2016 @08:01AM (#11495884)
Cool stuff ! Nice to see the range upgrade between Tesla s70 and s85