Using Claude Code since April has certainly benefited me... Can't see me ever going back to hand coding.
On Tue, 8 Sept 2026 at 12:12, Ralph Corderoy <[email protected]> wrote: > Hi, > > I thought this paper may interest the professional coders on this list > on their lunch break. > > Computer science achievement and writing skills predict > vibe coding proficiency — https://arxiv.org/abs/2603.14133 > PDF: https://arxiv.org/pdf/2603.14133 > > I haven't read every word, but skimmed it for interest; ‘Just looked at > the pictures’. > > Table 3 on page 11/17 sums it up, though I find the triangle ordering > doesn't make it as clear as: > > 0.417 Cog./CS > 0.365 Cog./Writing > 0.352 Cog./Vibe > > 0.386 CS/Vibe > > 0.290 Writing/Vibe > 0.126 Writing/CS (p=.213) > > These are the Pearson correlations between ‘computer-science > achievement, cognitive ability, writing skills, and vibe-coding > performance’. All have p<=0.03 showing the correlations are significant > apart from the one listed above saying there's no connection between > writing skill and computer-science achievement. > > So if you're smarter than the average bear, know computer science, and > can write well then using an AI to code should be a benefit. Life in > you old dogs yet. And some of us not-so-young ones. > > -- > Cheers, Ralph. > > -- > Next meeting: Online, Jitsi, Tuesday, 2026-10-06 20:00 > Check to whom you are replying > Meetings, mailing list, IRC, ... https://dorset.lug.org.uk > New thread, don't hijack: mailto:[email protected] > -- Next meeting: Online, Jitsi, Tuesday, 2026-10-06 20:00 Check to whom you are replying Meetings, mailing list, IRC, ... https://dorset.lug.org.uk New thread, don't hijack: mailto:[email protected]
