Viewing profile — BinaryIgor

Exactly. Verification is not cheap at all

"I have a hard time imagining a future where knowing how to solve problems with computers and how to control the complexity of those solutions is less valuable than it is today, so…

That's a valid point - I largely agree with you, I can make it generate mostly corrected & acceptable code with a solid level of quality, given smaller & scoped features and detail…

I think that the bottom line is that the bottlenecks are - the specific model you use & your skills, experience and reasoning capacity (intelligence); and you control only the latt…

"Perhaps there are frontiers of digital addiction we have yet to reach. Maybe one day we’ll all have Neuralinks that beam Instagram Reels directly into our primary visual cortex, a…

It also the most portable - no codecs, no formats and standards; most English texts are just ASCII :)

Hunger and drive can definitely lead to unexpected initially results; they cannot replace relevant experience, but if somebody has at least done something similar, it's often worth…

What makes you think that they will just keep improving? It's not obvious at all, we might soon hit a ceiling, if we haven not already - time will tell. There are lots of technolog…

I don't know whether I would go that extreme, but I also often find myself faster writing code manually; for some tasks though and contextually, AI-assisted coding is pretty useful…

Are guardrails, CI/CD, to make code at least compile-able and require minimal quality standards also possible to change via PR or managed somewhere else? With this possibility, it …

Ahhh, the problem with incentives; maybe it's more the case that, had the Linux Foundation behaved in a more aligned with the pure open-source ethos way, Linux would not be so wide…

Exactly this; for some tasks, it can speed up you dramatically, 5 - 10 x; with others, it actually makes you slower. And yes, very often writing a prompt + verifying results and po…

"The counter-scenario: as AI handles the routine 80%, humans focus on the hardest 20%. Architecture, tricky integrations, creative design, edge cases: the problems machines alone c…

Weird - it should be completely up to the developers, whether they write code by hand or partially/mostly with LLMs. If the code meets set standards and the author understands it a…

I have similar experiences with Claude Code ;) Have you used it as well? How does it compare?