I really want to use better fonts for my sites but the double page render showing one font while it loads the actual font just looks so unprofessional and jarring.
I thought this site being a typography focused site would have a better way to deal with it's still as bad as I remember it.
Doesn't stop them going to your employer and that hint of you doing something iffy is enough to claim you're bringing the company into disrepute by drawing unwanted attention.
Have you tried using an additional agent to verify the outputs? It seems that can help if the supervising agent has a small context demand on it. (ie. run this command, make sure it returns 0, invoke main coding agent with error message if it doesn't)
No stock backed company will be paying developers more regardless of much more productive these tools make us. You'll be lucky if they pay for the proper Claude Max plan themselves considering most wouldn't even spring for IntelliJ.
I wasn't thinking about this from the perspective of an IC in a company, more from the perspective of self employment or side projects. But its not any different for a larger business: An IC should not pay for their own tools, but an engineering manager who won't is a fool.
Sounds a lot like paying for online ads, they don't work because you're not paying enough, when in reality bots, scrapers and now agents are just running up all the clicks.
You pay more to try and get above that noise and hope you'll reach an actual human.
The new "fast mode" that burns tokens at 6 times the rate is just scary because that's what everyone still soon say we all need to be using to get results.
Here I am mostly writing code by hand, with some AI assistant help. I have a Claude subscription but only use it occasionally because it can take more time to review and fix the generated code as it would to hand-write it. Claude only saves me time on a minority of tasks where it's faster to prompt than hand-write.
And then I read about people spending hundreds or thousands of dollars a month on this stuff. Doesn't that turn your codebase into an unreadable mess?
I'm not getting results. That's the point. Claude doesn't fucking work without human intervention. When left to its own devices it makes bad decisions. It writes bad code. It needs constant supervision to stop it from going off the rails and replacing working code with broken code. It doesn't know what it's doing!
It's about as far as you can get from being able to work independently.
Yegge is an entertainer. Gas Town is performance art, it's not meant to be taken seriously.
Why is everyone obsessed with Mac Minis. They're awesome but for the work that these people are attempting to do? Just seems... nonsensical. Renting a server is cheaper and still just as "local" as any of this (they want "self hosted", I don't think anyone cares about local. Like are people air gapping networks? lol)
And a senior director of Nvidia? He had several Mac Minis? I really gotta imagine a Spark is better... at least it'll be a bit smarter of a cat (I'm pretty suspicious he used a LLM to help write that post)
It seems like the monkey-ladders story. Someone probably just had one sitting around and it worked or needed to do something Apple-specific and that message got lost along the way
I've been thinking about this recently and it seems like the most enthusiastic boosters always suggest difference in results is a skill issue, but I feel like there are 4 factors which multiply out to influence how much value someone gets:
- The quality of model output for _your particular domain / tech stack_. Models will always do better with languages and libraries they see a lot of than esoteric or proprietary
- The degree to which "works" = "good" in your scenario. For a one off script, "works" is all that matters, for a long lived core library, there are other considerations.
- The degree to which "works" can be easily (best yet, automatically) verified.
- Techniques, existing code cleanliness, documentation etc.
Boosters tend to lay all different experiences at the feet of this last, yet I'd argue the others are equally significant.
On the other hand, if you want to get the best results you can given the first 3 (which are generally out of one's control) then don't presume there's nothing you can do to improve the 4th.
The flood of Disney+ cancellations likely contributed to their decision to back down on Kimmel, kind of heartening to know we've still got some power over these mega corps.
writing any git command, ever, writing any documentation, ever. writing comments in issue trackers, resolving issues in issue trackers, doing pretty much anything in the terminal, ever… basically every imaginable thing which takes time away from the actual job
Why not say “using a computer”. gcl (my alias for git clone) is way faster to use than any prompting. Any use case I found for LLMs, I noticed that a good script or a DSL (as an abstraction) would be way more useful.
A lot. I often study software I use (mostly OSS) to find how a feature is implemented.
If something is cumbersome and I find myself needing it often (or I think I will need it), I write an alias, a script, an emacs function, etc,... That's the magic of reducing lot of steps to a single button press (or a short command).
I thought this site being a typography focused site would have a better way to deal with it's still as bad as I remember it.
reply