https://en.wikipedia.org/wiki/Apple_in_China

If we keep this up, someone's bound to jump in with a brag about memory cores and punchcards.

For a while I've been meaning to set up some Wireguard connections among some of my systems. Being as busy as I am with work and family, I've relinquished that to Tailscale for now.

Sure, I could have sat down and jumped through the hoops to get everything set up and working across my various hosts, including network routes, firewall rules, key pairs, systemd units, and so forth. But the "cheap and easy" alternative was right there and worked (except when it forces re-authentication).

With LLM agents, I was able to effortlessly analyze my existing network and produce tailored scripts to do precisely what I wanted. All I had to do was review the scripts for potential security issues and what not. Looking at the script, there are 3 or 4 specific tweaks that needed to be made to my network routing rules given my network topology. I could have read a few man pages and iterated on the script by hand to eventually get there after maybe an hour or two of futzing.

The availability and effectiveness of the agents is simply too tempting for me. I'm not sure what this means about my skillset, or if that even matters any more. I am fairly confident that, so long as my brain still works well enough, I'll always be able to RTFM and figure things like this out myself. At this rate I wonder whether my kids will have the same ability. And I also wonder how much that will matter.

Regardless, I'm still helping them figure things out the "old way" without over-reliance on LLMs. One thing I'm fairly certain about is that failure to develop problem-solving skills can only put them in a worse position in life, no matter how capable AI becomes.

That said, for the very few people who don't respond to traditional drugs, HSCT is better than the alternative, which would be a horrific steady loss of function as your immune system chews up your central nervous system.

Although the cynical part of me says that this will result in malicious actors trying to trick agents into giving out a bunch of micro payments. There are counter defenses that can help detect and compensate for that, but perhaps the best we will be able to do is prompt user with the default agent recommendation.

In short, I hadn't prepared at all for the interview loop, so I didn't have any of the standard responses "ready to go" for the behavioral interview. We ended up meandering into a bunch of stuff from my personal life, and I didn't have the presence of mind to course-correct it myself. It didn't help that the interviewer actively encouraged me to keep talking about the personal non-work experiences. I got the impression that the interviewer was self-deluded into thinking that they could do some kind of psychological evaluation of me, even though they clearly (in hindsight) had no formal education or training in doing that sort of thing.

Anyway, same story. After a few days, generic rejection letter, and no more communications. I can only imagine my interview loop feedback must have been horrific to overcome what I am certain was a strong internal referral by a very senior and well-respected employee at said company who I had worked with closely for several years (and he'd sung my praises at our previous company many a time when giving perf feedback). I keep replaying the behavioral interview in my mind and realize I must have come across really awkwardly to the hiring manager. In the end I felt much like the author of this blog post did, personally rather than professionally rejected.

I'm resolved no longer suffering pseudo-psychological behavioral interviews. If I get any questions that I feel cross the line between professional and personal, I'll firmly respond that I do not feel comfortable discussing non-work-related issues in a job interview.

That means that I ride alone these days. I did not renew my membership this year.

The last time I experienced something like this was when Facebook starting being the only way to participate in certain events. Back when that happened, I simply counted myself as excluded and did other things with my time and money.

https://www.idoc.idaho.gov/content/prisons/resident-client-s...

Some of his blog posts in the past several months also highlight the dismal state of prison tech, which I suppose is on-point for this thread:

https://www.sevarg.net/

The same way this sort of thing has always been accomplished: Government regulation.

Vote, write reps, donate to the ACLU and EFF, socialize.

The Waymo rides were near-perfect. At one point when a delivery truck was blocking 3 lanes, the vehicle assertively merged over into the free lane to get around. A couple of people on e-bikes were all over the place, but at no point did I feel that the vehicle put them in any kind of danger. Starts, stops, and turns were all smooth. End-to-end time was good, the ride itself was comfortable, and the price was reasonable.

On the other hand the Uber driver picked me up in a Tesla that had regen cranked up. They continually accelerated and decelerated the entire way to the airport, rocking the car back and forth the whole time, as if it were a nervous habit to continually press and release the accelerator or something. I felt sick by the time we got to my terminal.

For me at this point, technology like Waymo can't carpet every metropolitan area quickly enough.

One caveat: I should be able to use it (and, hence, pay for it) anonymously.