any · textlog

even vanguard supports passkeys now investor.vanguard.com/…/trust-security

This bout of COVID is more like “Corona Light” compared to previous years, but I’m still spending most of it in bed. Stay safe out there.

wrote:

weekend plans are:

attend to the pending work that I am avoiding around home
improve my understanding of using agents in claude code and codex cli
dig into navier stokes equations from the first principles (I am excited for this)

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 i’m happy to settle into predictable models for a while.

replied to:

I’ve found the same, albeit with Opus — it’s hard to find uses for Fable. I don’t 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.

replied to:

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.

…

replied to:

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.

replied to:

Coding probably yeah, but still they are bad at generating novel information, new ideas and such. They’re also not very good at seeing the bigger picture, they will narrowly perform the task but they’re not taking into account future revisions, which ends up in refactor after refactor in order to move forward.

wrote:

Getting that naneinf in Balatro is pain. 😅

wrote:

Installed Hermes Desktop and starting to build out my team of bots. My experience with Hermes so far has been great: it keeps surprising me by being what i need it to be ... but I'll reserve a final judgement until after a proper period of use.

wrote:

Anthropic is announcing the end of the world every few days. All this marketing disguised as news about an impeding danger of AI is tiresome.

……

replied to:

not marketing. yes their jobs positively select for concern about ai, but most people that are actively researching the field are concerned about the current state of safety, pace and incentives. I dont agree with a lot anthropic does, but i do believe the employees take safety seriously and they obviously have a better understanding of it than us. also theres no incentive for someone like coxon to sound alarm bells on twitter for "marketing" reasons, after quitting anthropic

replied to:

Yes, but some people say that they are pushing for market regulation. They want the state to protect them from the chinese models and, also, to protect the massive investments in Anthropic, OpenaAI, et al. that these companies will never be able to return. This sounds plausible to me too.

replied to:

Maybe but it would be convenient for them if they were the only ones allowed to train new models. I think that's much more likely what they're interested in.

…

replied to:

read darios latest post. its not what they are after. its really not that complicated, the technology is simply if development continues to race as it is right now. they are already doing most of what they can to stop china from ai dev.

wrote:

Today visiting Zaragoza with an aunt and my mom, I hope to be this willing and capable of moving around for leisure when I'm in my 60s too

wrote:

@@@@@@@ @@@@@@@@ @@@ @@@ @@@@@@@ @@@ @@@@@@ @@@@@@@ @@! @@! @@! !@@ @@! @@! @@! @@@ !@@ @!! @!!!:! !@@!@! @!! @!! @!@ !@! !@! @!@!@ !!: !!: !: :!! !!: !!: !!: !!! :!! !!: : : :: ::: ::: ::: : : ::.: : : :. : :: :: :

wrote:

Sharing a link to my music blog: crusty-metallian.net Not a lot of content yet, it's a work in progress :)

replied to:

Big list of events you've attended! Definitely dump more photos when you find the time. I'm more of a casual Nu-Metal enjoyer myself, but I can also appreciate some of the classics.

replied to:

It's taken me 5 years to get a photo storage engine off the ground. I've got it now, so I now have to go back through time and get the photos up. AC/DC next Thursday!

wrote:

Are tokens an equivalent of work? Like a currency and therefor a tool to steer and prioritize work in large orgs. Hypothesis: In the end all workpackages will consist of 1 accountable human and 99% tokens burnt by an ai.

wrote:

Up up and away. Not sleeping, ok. Run run and breathe. Not waking, leave.

wrote:

"Everything worth doing is worth doing badly." Meditate even if you have the time, even if you can only do two minutes. Train even if you're tired and you're not gonna do it well. Start that project even if you're not ready. Don't wait for perfection.

wrote:

my beautiful Vulpes Inculta.. oh how I miss him...

wrote:

It's one of the sad ironies of this computer stuff that the simpler solutions take longer to conceive than the complicated ones.

wrote:

Bluey's "" is an ingenious way to save . The scheme is simple: One night a week, we make twice as much and drop it off at the other family's house. They do the same on a different night.The is deceivingly simple. Doubling a recipe is easier than preparing a second dish.

wrote:

I want to become an excellent marketing person😭😭

Any conversation