Re:In 27,280 coding agent runs, 64% of inference spend went ...
by yugoslavia4ever on Tuesday November 17, 2026 @11:55AM
(#50534357)
Yes, but before you learned as you went, researching and finding out what good (or at least better) looked like; what learning is done when you wave your hand?
Re:In 27,280 coding agent runs, 64% of inference spend went ...
by ygjb on Tuesday November 17, 2026 @10:29PM
(#50541493)
Honestly? I have more time to learn now than I did before. I can also do something that was really challenging before LLMs as well, which is turn my lack of comprehension into an demand, guided tour through a Socratic exploration of the unknown topic, including generating labs specific to the skills I want to develop and with the resources I have available.
It's like anything else with LLMs, if you treat it like a magic wand, you haven't really learned or built anything, but using it as a true assistant, it can be a powerful and flexible tool.
I think the quality of the results vary with the rigor of the process. If you one-shot prompt a new service (even with Fable5) "build me an airtable competitor, no bugs", you will get some real code camp quality results, but a well defined set of prompts and a workflow that leverages multiple coding agents reviewing each others work, and implementing test cases at a relatively granular level yields radically different results.
Couple that with a rigorous design/spec session, and multiple checkpoints (say at release milestone) to monitor drift from the original design makes the process a bit more intentional and measurable, while still being far faster than a typical engineer can build.