Hacker Neue

Preferences
simonw parent
I think the productivity improvement you can get just from having a decent LLM available to answer technical questions is significant enough already even without the whole Agent-based tool-in-a-loop thing.

This morning I used Claude 4 Sonnet to figure out how to build, package and ship a Docker container to GitHub Container Registry in 25 minutes start to finish. Without Claude's help I would expect that to take me a couple of hours at least... and there's a decent chance I would have got stuck on some minor point and given up in frustration.

Transcript: https://claude.ai/share/5f0e6547-a3e9-4252-98d0-56f3141c3694 - write-up: https://til.simonwillison.net/github/container-registry

nemothekid
I'm not denying LLMs are useful. I believe the trend was going to happen whether regardless of how useful LLMs are.

AI ended up being a convenient excuse for big tech to justify their layoffs, but Twitter already painted a story about how bloated some organizations were. Now that there is no longer any status in having 9,001 reports the pendulum has swing the other way - it's now sexy to brag about how little people you employ.

homebrewer
Their boilerplate works out of the box, you don't need to change anything. I recently packaged, signed, and published an OCI container into ghcr for the first time, it took about 5 to 10 minutes without touching any LLMs thanks to the quality of their documentation.
jordanb
Eh I felt that way about the internet in 2010s. Seemed like virtually any question could be answered by a google query. People were making jokes that a programmer's job mostly consisted of looking things up on stack overflow. But then google started sucking and SO turned into another expertsexchange (which was itself good in the 2000s).

So far from what I've experienced AI coding agents automate away the looking things up on SO part (mostly by violating OSS licenses on Github). But that part is only bad because the existing tools for doing that were intentionally enshitified.

tasty_freeze
> expertsexchange

My vote for the unintentionally funniest company name. I wonder if they were aware when the landed on it, or if they were so deep in the process that it was too late to change course when they realized what they had done.

Izkata
They're still around, long ago they bought the "experts-exchange" domain name and redirected the original, then at some point after that they abandoned the original entirely.
sothatsit
I wonder whether we will avoid some enshittification of AI because people are willing to pay for it. It doesn't all have to run off ads (although I'm sure all the free tiers will contain ads eventually).
data-ottawa
Conceptually I find LLMs/AI broaden my skillset but slow down any processes that are deep in specific knowledge and context.

It is really nice to have that, it raises the floor on the skills I'm not good at.

This item has no comments currently.