"The first time I used ChatGPT to code, back in early 2023, I was reminded of " The Monkey's Paw," a classic horror story about an accursed talisman that grants wishes, but always by the most malevolent path - the desired outcome arrives after exacting a brutal cost elsewhere first. With the same humorless literalness, ChatGPT would implement the change I'd asked for, while also scrambling dozens of unrelated lines. The output was typically over-engineered, often barnacled with irrelevant fragments of code."
"The trick is to keep the problem space constrained. I recently had it take a dozen lines of code, each running for 40 milliseconds in sequence - time stacking up - and run them all in parallel so the entire job finished in the time it used to take for just one. In a way, it's like using a high-precision 3D printer to build an aircraft: use it to produce small custom parts, like hydraulic seals or O-rings, and it delivers flawlessly;"
Early uses of ChatGPT for coding produced literal but harmful modifications, scrambling unrelated lines and over-engineering solutions with irrelevant fragments. Recent AI-assisted tools behave like highly capable, deferential coding interns that excel at localized changes but can make sweeping, excessive edits. Keeping problems tightly constrained yields the best results, enabling tasks such as parallelizing short sequential routines to reduce runtime dramatically. The analogy compares AI to a high-precision 3D printer that builds small components flawlessly but fails at complete assemblies. Vibe-coding enables nonprofessionals to produce varying-quality products, continuing the lineage of no-code tools; major vendors have released dedicated apps.
Read at The Verge
Unable to calculate read time
Collection
[
|
...
]