I got so angry at Fable's verbosity that I had a non-Anthropic model vibe-code a dedicated English linter. One that threw spaghetti at the wall in the form of combined Flesch-Kincaid, Gunning Fog, SMOG, Coleman-Liau, ARI and a whole pile of regexes and NLP as a fast Simple Technical English Gate. It also incorporates nicely into other agent projects, like for comment and README linting.
So if it gets bad I simply tell it "I ain't reading all that, feed it through the STE Gate" and it will tame the results. I haven't bothered to set it up as a hook yet.
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.
It would be neat to also include NVFP4 variants for the Blackwell hardware.