Today, I wrote a new Business Continuity Plan, worked with my SRE manager to improve responses to alerts, got a cringe email from HR and have to tell my staff to RTO 3-days a week if not classified as remote. Worked out for my 8th day streak, and cuddled in bed with my girl.
Hello World
Determine what matters most and make a list of the no more than 7 things.
Do one thing well at a time, top down. Reprioritise as you learn more.
Notes:
If you half-arse a task and decide that'll do, it's evidence it wasn't the right priority. Learn.
Any sort of productivity, multi-tasking, app, solution type thing is a scam or a money grab and isn't needed.
People tend to remember 7 things well, but struggle with longer lists and particularly fail to remember things in the middle.
My first post on Twitter in 2007 or so was kinda about the utility of broadcasting what was on my mind. :)
@tel๐ดprofilefollowI really enjoy learning, I really enjoy making. I'm learning to be less guarded.wrote:
a constant, existential pull
so old I couldn't tell you the end
or draw its shape
between kind acceptance
and striving, struggling, writhing, climbing
learning, growing, discontent
"do you feel this way, too, at endless war with longing itself?"
but the birds and trees and ants and wind
in their own marvelous design
don't reply #poemnotesfollow
@javisrike๐งโ๐profilefollowSoftware โข maker projects โข music โข DIY
Mostly figuring things out as I go.wrote:
ai coding feels like it has reached diminishing returns for me. luna is my default orchestrator, routing work by complexity. in practice, usage lands around 16% luna, 48% sol, 30% astra, and 6% terra. at this point, i care less about each new frontier release. the system already finds a capable model for the job. the frontier is moving beyond my day-to-day work, so iโm happy to settle into predictable models for a while.
#ainotesfollow#programmingnotesfollow#agentnotesfollow#technotesfollow
Iโve found the same, albeit with Opus โ itโs hard to find uses for Fable. I donโt need a model that works for longer or works on harder problems, I need one that consistently produces simple, easy to understand, code; which at this point none of them do.
I've been there since I settled on a combination of GLM, DeepSeek and MiMo for planning, implementation, and verification flows.
I'm a lot more interested at this point in having cheaper models that can consistently do the work I need. It's been a while that I hanven't noticed any improvement when I try new frontier models. I only notice they are very expensive.
same here, for almost an year. At this point, I could easily live with models that were released 6-12 months ago and continue doing so.
also possibly the reason why the current focus has been around agentic workflows or agentic anything, than the model capabilities.
Coding probably yeah, but still they are bad at generating novel information, new ideas and such. Theyโre also not very good at seeing the bigger picture, they will narrowly perform the task but theyโre not taking into account future revisions, which ends up in refactor after refactor in order to move forward.
@tel๐ดprofilefollowI really enjoy learning, I really enjoy making. I'm learning to be less guarded.wrote:
I've been on a kick lately of trying to visualize the oscillating clock, and ultimately the effectively arbitrarily complex activity of a computer processor, as modern refinements of the line shaft factory of the 19th century. Of compute as being not much more than profoundly refined "work" delivered by the electrical grid into marvelously complex machines.
Does that, as a metaphor at least, feel as important to you as it has to me of late? We spend so much time in a world abstracted.
I never have enough time but Iโd love to do a bit more recreational programming with esoterical languages like kitten, #uiuanotesfollow, and #jqnotesfollow. AoC and Project Euler are good because they just require an answer but thereโs also loads of simple puzzles online that rely on being able to submit the code in common languages. Iโve been wondering, however, if I could use an LLM to take those problems and create a verification harness for any language I like.
Trying to gently work my way back to the target intensity needed for the Norwegian 4x4 to get my weekly dose of suck and feel accomplished after. Chronic left leg pain unfortunately likes reminding me it's there though.
Turned Stepper (self-hosted AWS StepFunctions) into client-server. Server hosts state machines, clients poll for tasks. New resources about running #claudenotesfollow. claude -p works, now thinking if I need interactive session management.