Dr. Wesker

I recently revived a circa-2014 Thinkserver with a core install of antiX, and was pleasantly surprised. I went for the smallest footprint possible by installing only the core distro, and then choosing the packages I wanted/needed.

I have all my services spun up in docker containers, which makes it easier to pick and choose which services use Tailscale and which use a VPN. I guess I haven’t yet been put in a position where I wanted one to use both.

Tailscale’s free offering goes a long way.

I’m just thinking if you got nicked and didn’t have a chance to reboot into an encrypted state, or otherwise the device was compromised outside the house.

Y’all aren’t worried about having a tunnel into your (likely questionable) servers, on your mobile devices?

Fighter of the Night Man

Yeah.I’m gonna go with block on this one. Thanks.

Some other weird bot user posted this earlier, to an incorrect community. Are you a bot as well?

Excel

Nah dawg.

But at a certain point, it seems like you spend more time babysitting and spoon-feeding the LLM than you do writing productive code.

I’ve found it pretty effective to not babysit, but instead have the model iterate on it’s instructions file. If it did something wrong or unexpected, I explain what I wanted it to do, and ask it to update it’s project instructions to avoid the pitfall in future. It’s more akin to calm and positive reinforcement.

Obviously YMMV. I am in charge of a large codebase of python cron automations, that interact with a handful of services and APIs. I’ve rolled a ~600 line instructions file, that has allowed me to pretty successfully use Claude to stand up from scratch full object-oriented clients, complete with dep injection, schema and contract data models, unit tests, etc.

I do end up having to make stylistic tweaks, and sometimes reinforce things like DRY, but I actually enjoy that part.

EDIT: Whenever I begin to feel like I’m babysitting, it’s usually due to context pollution and the best course is to start a fresh agent session.

This is extremely valid.

The biggest reason I’m able to use LLMs efficiently and safely, is because of all my prior experience. I’m able to write up all the project guard rails, the expected architecture, call out gotchas, etc. These are the things that actually keep the output in spec (usually).

If a junior hasn’t already manually established this knowledge and experience, much of the code that they’re going to produce with AI is gonna be crap with varying levels of deviation.

It’s been my experience that the quality of code is greatly influenced by the quality of your project instructions file, and your prompt. And of course what model you’re using.

I am not necessarily a proponent of AI, I just found myself being reassigned to a team that manages AI for developer use. Part of my responsibilities has been to research how to successfully and productively use the tech.

This baby fit only serves to get yourself blocked by people who would otherwise have continued interact with you.

I’ve been thinking about hosting a Quake II server, lately.

EDIT: Or Unreal Tournament. Both were my jam back in the day.

End passwordlessness.

Greate writeup.

Don’t ever mention OOP during an interview. I swear it’s such an odd topic of contention, you will flat out get passed up for mentioning it in any sort of positive light.

Yet if you employ the paradigm cleanly and in the right context, devs get impressed and start borrowing designs.

So weird.

In India AI outsource you.

Took me a second.

Hell yeah.

Google

I have identified the problem.