The “craftsman to Ikea factory manager” line from the interview is the real headline here. AI does the fun creative stuff, you get stuck reviewing 2000 lines you didn’t write. Revert rate tells you more than any “10x” claim.

It often takes me 3-4 iterations with a coding assistant once you get to a working solution, to get one that still works but is simplified down ditching >80% of needless complexity introduced in the first take.

Many stop at the first thing that works. This is totally fine for code that will run once to get a result and then be discarded. But if that code is going into a product or service that will be maintained, you have to have the knowledge and the will to push further until you have not just a working but a lean, clean and simple solution.

GIGO very much still applies.

The tech debt this title speaks of only applies if humans have to deal with it. Tech debt is an assumption made on the grounds that humans are still programming and AI does not evolve. It's the opposite of reality.

Coding agents are such a congested space right now that to me this mostly reads as an advertisement.

From the guys who don't understand that people don't like to see their questions closed as a "duplicate" of an unrelated question.

Non-native speaker here. Is the phrasing of the blog title awkward or am I the only one? Seems like they are using "10x" as a verb and my brain kept parsing "10x" as a adjective to developer, reading "10x developer" which is a already established industry lingo.

I’m so sick of “10x” everything. It’s almost always grossly overstated marketing bullshit. There are a lot more precise x’s, but everyone just rounds up and snaps to 10x. And the numbers aren’t even really ever truly measured. Thumb in the wind.

bUt AI mAkEs mE cOdE fAsTeR

how do we pay this debt?

One of the earlier references to the 10x that I've found is in

https://www.scribd.com/document/557220119/NNPP-Article

> Researchers have found between a low of 5 to 1 to a high of 100 to 1 ratios in programmer performance. This means that programmers at the same level, with similar backgrounds and comparable salaries, might take 1 to 100 weeks to complete the same tasks. [21, p. 8]

> The ratio of programmer performance that repeatedly appeared in the studies investigated by Bill Curtis in the July/August 1990 issue of American Programmer was 22 to 1. This was both for source lines of code produced and for debugging times - which includes both defect detection rate and defect removal efficiency. [5, pp. 4 - 6] The NNPP also produces a higher instance of defects in the work product. Figure 1 shows the consequences of the NNPPs.

The reference to 21 is Shneiderman, Ben Software Psychology: Human Factors in Computer and Information Systems (Cambridge, MA: Winthrop, 1980) and 5 is Curtis, Bill, "Managing the Real Leverage in Software Productivity and Quality", American Programmer July/August 1990

https://archive.org/details/softwarepsycholo00shne/page/8/mo... - this then goes into an entire book of sources and research.

There's also mention of DeMarco and Lister in some literature... which means Peopleware.

From there:

> While this [10 to 1] productivity differential among programmers is understandable, there is also a 10 to 1 difference in productivity among software organizations.

> H. D. Mills, Software Productivity (New York: Dorset House Publishing, 1988), p. 266.

> Our study found that there were huge differences between the 92 competing organizations. Over the whole sample, the best organization (the one with the best average performance of its representatives) worked more than ten times faster than the worst organization. In addition to their speed, all competitors from the fastest organization developed code that passed the major acceptance test.

> This is more than a little unsettling. Managers for years have affected a certain fatalism about individual differences. They reasoned that the differences were innate, so you couldn’t do much about them. It’s harder to be fatalistic about the clustering effect. Some companies are doing a lot worse than others. Something about their environment and corporate culture is failing to attract and keep good people or is making it impossible for even good people to work effectively.

In one of the book on "10x myth", the author bluntly states that there is no objective way to measure "productivity". So any such report is purely subjective. Its a fascinating argument. I don't remember the book, but this author had actually read the papers while researching and based his conclusion of the research papers

As far is reality is concerned, the differences between average and skilled can be as much as 100x or more. It can be even more if you consider that some people add negative productivity

It means how many Mountain Dews you can chug per day.

Agreed. My developers go to eleven.