Interesting insights about similar issues in this video by Openrig [1]
Multi-agent coordination is an engineering problem characterized by the inevitable emergence of human-like social pathologies - such as bureaucratic inertia.
> human-like social pathologies - such as bureaucratic inertia
Isn't bureaucracy just the sociological manifestation of synchronization overhead? Sounds shortsighted to file it away as just some weird social pathology that emerges out of nowhere specifically affecting humans.
No, bureaucracy also includes elements of social dominance by people who have no other means to assert status (or sometimes outright covert sadism), busywork, and processes that are rule-based - often dumbed down in the hope that people with limited intelligence don't make avoidable mistakes - rather than responsive and reality-based.
Getting agents to deal with their own versions of these issues is an interesting experiment.
I personally find that to be a bit of an inversion. People will utilize leverage and identity in whatever context, so mixing that in doesn't seem cogent to me.
But maybe the two are genuinely tied together enough that it's deserving to be a part of the definition, I don't know. Tried looking up the definition, I'm not really convinced.
For the longest time I considered the "hate on bureaucracy" more of a reactionary trope rather than anything actually coherent. Maybe this is just another one of my cultural differences of many. It's not as if people forming consensus, keeping count, or delegating authority were ever actually possible (or desirable) to escape, comes with scale. So to try and paint it as some odd devilish plague always came across to me as dilettante, though maybe it's more me who's simply never grasped the whole dynamic and the cultural position around this fully.
A random book from the collection looks interesting: Correction by Thomas Bernhard.
Described as “a mesmerising, claustrophobic novel about obsession, genius and the impossibility of perfection. Structured in two enormous, uninterrupted blocks of prose, it follows an unnamed narrator reconstructing the life of his dead friend Roithamer, before becoming absorbed in his manuscripts. Sentences spiral, repeat and contradict themselves, creating the sensation of being trapped inside an endlessly turning mind. Roithamer is modelled partly on Ludwig Wittgenstein, particularly his intellectual austerity and obsessive pursuit of perfection, reflected in his design of an extraordinary house for his sister. A darkly comic, exhilarating and exhausting masterpiece.”
Bernhard is fantastic. Woodcutters might be a gentler introduction to his style. It's shorter, funnier, and less oppressive than Correction, which is his magnum opus. Apparently he was at least somewhat as unhinged in real life as in his writing. He was notorious for insulting the Austrian intelligentsia and either refusing literary awards or showing up at the ceremony just to rant and insult the audience, which he wrote about in a memoir titled My Prizes. He was a big influence on W.G. Sebald, another great German language writer (my personal favorite) who makes an appearance in McCarthy's library.
McCarthy made his famous dismissal of Proust and Henry James in the NYT in 1992 and in the Oprah interview, on the grounds those writers didn't deal with deep issues of life and death. But from all that has been revealed about his personal library, including this Bernhard book, one wonders if that was a put-on.
Surely he meant their work. Dealing with deep issues of life and death in his work didn’t require him to be serious all the time about every topic in his own life.
You'll love Correction if you have a taste for experimental literature. I've have all of Bernhard's novels. They are (mostly) uninterrupted walls of text. They can also be quite depressing. You'll likely either love them or hate them. Correction is probably the most exemplary instance of his style and experimentation, and maybe his best novel, but Concrete and Extinction fall into this category as well. Wittgenstein's Nephew, Frost, and Woodcutters are more approachable if you want to ease into it. Starting with Correction might be a bit off-putting and intense depending on how often you read more experimental/stylistic literature.
I like Bernhard. I also recommend The Lime Works and wittgenstein’s nephew if you like correction. I found Bernhard through Thomas Ligotti. For Ligotti I recommend teatro grottesco and if you want to dive off the deep end the conspiracy against the human race.
I was prescribed diazepam and it was an important part of my healing when I suffered a back injury. The doctor prescribed the 'holy trinity' for severe back pain: diclofenac for anti inflammatory, cocodamol for pain and diazepam to control muscle spasms and help me sleep. It worked like magic.
The doctor gave me the minimum amount of pills to get me through the initial chronic period, 7 days, and I was very grateful to be made comfortable.
I was lucky that my back healed quickly, even after a few days on the drugs I detected a feeling of dependency creeping up.
TDK C-90 10-packs were my favourites as a teenager in the 80s in Australia. And for an extra dose of nostalgia, here is the "TDK does amazing things" ad from 1984.
> For day-to-day developer work, it’s totally viable to focus on one or two flash-tier cheap models
GLM 5.3 flash has been good as my default profile Hermes bot, after I readjusted its memory to point to a couple of key skills.
I got some great coding results with GLM 5.2, and 5.3 Flash is supposedly almost as good, so I will be trying it out soon for day to day tasks as the post advises.
I've been using GLM 5.3 Flash quite a lot for coding this month since they've had their promotion running. It's been tackling some difficult stuff - coding up a Julia version of the luminal GPU kernel optimization package, FPGA work with Verilog (including getting a BitNet 2B model running on FPGA - that one's been split between Claude and GLM), coding up a Julia version of DiffLUT. It's been handling these tasks pretty well. I do move between Claude Sonnet 5.5 & GLM 5.3-flash on the BitNet one based on what's available.
It's still in process so we're not getting tokens out of it yet. Targetting a Gowin 138K (the Tang Retro Console 138K board). This is moving from a Xilinx part that's about 2x that size so we have to trade some time for space. Estimated to be in the 7tok/sec when it's all said and done. Not super fast, but this isn't a super fast (clockrate) FPGA. And at 138K LUTs it's pretty small for this kind of task (but it is the largest FPGA that I've got, and the boards are quite affordable at $129 which includes 8GB of DDR3 - which is another reason it's kind'a of slow, DDR3 is kind'a slow)
> Nobody in this ecosystem, I thought, is actually in control here.
Profound, your comment provoked this thought: we know that AI in organizations is disruptive, but we still don’t understand some of the shifting patterns of power, communications, agency, etc.
If AI is not well-suited for traditional models of stratified management then maybe we need different models of bureaucracy?
Sorry the UI on Mobile is work in progress and currently, it's not accessible via Mobile (small screens); my plan is to creeate a special touch friendly UI for mobile and I haven't finished the concept (UX wise).
Multi-agent coordination is an engineering problem characterized by the inevitable emergence of human-like social pathologies - such as bureaucratic inertia.
[1] https://m.youtube.com/watch?v=AL-PQuB2wy0