With a 4-bit quant of GLM-5.2, I can get about 0.8-1.1 tok/s on an underclocked dual Xeon E5-2698 v4 with 512GiB of DDR4-2400. I think it was specifically a Q4_K_M quant. Of course, the time-to-first-token is absolutely atrocious.
Which is completely insane for a ten year old configuration.
Most of my past roles had very simple code at the important deliverable level, on bizarre and arcane platforms that would have little context for frontier LLMs. Most the creativity and complexity was in tooling for research/development/testing.
Agentic coding could help a lot for the latter, not necessarily the former.
Human insight can emerge from attacking the semblance of sense in the LLM's output.
Much of the cognitive work in writing emerges in the labor of writing prose and challenging assumptions against the model you build in your head as you go. I've found this process is inverted when working with an LLM: it in effect emits a provisional structure first, and I discover what I actually think by finding where its output is vague, overconfident, incomplete or outright false.
Accepting surface-level coherence as finished thought is the failure mode to avoid.
Yeah I've written some docs using the following process:
1. Throw some notes, PR links, etc. into copilot and ask for a first draft
2. Go back and forth for a while asking for revisions
3. Trash all of the AI-generated text and rewrite the whole thing myself from scratch, which I can do quickly in a typing frenzy because I now have a clear idea what I want, by way of seeing what I don't want.
Sure this is true. And if an AI draft helps in creating quality writing, great!
I was thinking more when it comes to stuff other people send me (like a freelance writer) and “editing” is basically writing the first draft because no cognitive effort has yet been spent on the piece
Yes! It has all the polish and flourish of something that has all the finishing touches, but none of the underlying structure your brain infers it to have due to its polish.
Elitist ivory tower as in free education for all that want it.
8th order effects like a well functioning society that isn't on the verge of collapse, where people live well, love each other, and think about interesting, important problems.
Distinct from the 1st order effects of a really high GDP thanks to all of the code monkeys we've trained to glue react components together: which has netted us a society on the verge of collapse, where poverty abounds, crime is universal, basic infrastructure like roads and water are crumbling, and we are plagued by mental illnesses, suicide, drug addiction, and mass shootings.
Hmm, if only there were any analogues in history that could show us the way forward, anyways, I've got to run, I've got a meeting in five with my agent who's going to show me how to 100x my SAAS revenue.
The latter is definitely more colorful, and reflects a parrot's tendency to glom on to patterns. "Not X, but Y" being one of the more infamous ones.
Once in frustration I called a certain frontier model "Sam Altman's Tin Bird" to another agent with memory, and ever since then that other agent refers to ChatGPT as "the tin bird". Definitely a RAG artifact more than an attractor in that case, but I found it amusing.
Tried it for while, works with GrapheneOS and Android Auto well enough.
What I absolutely can’t stand is the routing. It once tried to send me through residential Oakland on some Manhattan-grade staircase labyrinth instead of just taking normal streets.
EVE to me is an odd duck because it's an explicitly cutthroat universe - many people log on expecting monsters. There are a lot of supportive players out there among the trolls; where the knives of betrayal really come out is in the politics of player-controlled space.
What's weird is that I love EVE for that sort of nullsec drama and sociopathic players eating each other in crazed gambits, but a couple of matches in Overwatch competitive a decade ago put me off the idea of matchmaking lobbies altogether.
Which is completely insane for a ten year old configuration.
reply