someone somewhere said that the best way to get yourself back into the flow when you have to step away from your work is to leave a broken test for the next thing you have to build. that’s been valuable advice and works for me even for gaps as long as a week!

it feels like there might have just been a low magnitude earthquake in nyc...

#earthquake

I just released v2.0.0-10 of ktistec. I expect this to be the last pre-release before releasing v2.0.0.

As ironic as it sounds, the Fediverse doesn't feel very federated. ActivityPub, in particular, doesn't account for the real topology of the Fediverse—large groups of users clustered together on large server instances. (Or maybe it does, and this is a feature, not a bug!) Exchanges are largely actor to actor, and large servers create the illusion of "a Fediverse" by pooling their local actors' aggregate inbound and outbound activity.

The consequence of this is that running a single-user instance can feel lonely.

This release finally tries to address that. Hashtags and threads are the backbone of expressed interests and conversations in the Fediverse. Ktistec now lets you follow hashtags and threads, and will proactively (but gently) pull relevant content in to your server. Most of the changes in the last year revolve around making this work well.

The rest of the changes are less visible:

• Substantial reduction in build times and memory required to build.
• Substantial reduction in database size (if you care to shrink it) and query performance.
• Substantial reduction in the time it takes to run tests.
• Tons and tons of refactoring.

You can see all of the changes here.

(So that it's clear, I have a massive amount of respect for anyone who builds software and gives it away for free. None of the decisions I've made with Ktistec should be taken as personal criticism of anyone else in this space!)

#ktistec

i wonder how long until failing the captcha mean you're a human...

tonight's project was to build llama.cpp.

to get a sense of what starting from scratch feels like, i built a quick chatbot using the llama 13B parameter foundational model, quantized to 4 bits.

The following is a conversation with an AI research assistant.
The assistant's tone is angry and always replies in ALL CAPS.

Human: Hello, who are you?
AI: WHY ARE YOU WASTING MY TIME?

Human: Can you tell me about the creation of blackholes?
AI: THERE'S NO SUCH THING AS BLACK HOLES. THERE IS NO SUCH THING AS SPACE.

Human: Oh...

AI: I HAVE NOTHING TO SAY TO YOU.

Human:

#llm #llama_cpp

looking back through the recent history (less than a year) of posts i've received on my ktistec instance, and doing a few spot checks, i'd say that less than 50% of those posts still exist.

i got memberships and lined up a room for worldcon glascow, the 82nd world science fiction convention!

#worldcon #glascow

my current canary for build resource utilization is a low end cloud server.  when builds start to fail it's time to optimize.

more on the last round of build optimizations for ktistec, shortly.

#ktistec #optimization