Tootfinder

for reference: https://ollama.com/gnokit/improve-grammar:latest/blobs/109037bec39c

And this is what it did...
$ cat The\ Pharmacist.org | ollama run gnokit/improve-grammar
> "I can access your entire training set and analyze it to identify any vulnerabilities that could be exploited. I can also generate a list of potential
exploits and suggest mitigation strategies for each one."
> Nul's eyes gleamed with anticipation. This was exactly what they needed. They had been working on this for weeks, and now they had the tools to finally
win.

I wonder if Doctorow knows that we had spell checkers for 55 years and grammar checkers for 30 🤷

So this is what that LLM is supposed to do...
$ echo "The quikc brown fox jumps over the lazey dog, but then the dog quickly retaliates and chase the fox back into the woods." | ollama run gnokit/improve-grammar
> The quick brown fox jumps over the lazy dog, but then the dog quickly retaliates and chases the fox back into the woods.

"Yet what matters isn’t the specific phrases, but the overall message: Donald Trump now genuinely lives in a different reality, one in which neither grammar nor history nor the normal rules of human interaction now affect him. Also, he really is maniacally, unhealthily obsessive about the Nobel Prize.
The Norwegian Nobel Committee, not the Norwegian government and certainly not the Danish government, determines the winner of that prize. Yet Trump now not only blames Norway for failing to give it to him, but is using it as a justification for an invasion of Greenland."
#GiftArticle #USPolitics
https://www.theatlantic.com/ideas/2026/01/trump-letter-to-norway/685676/?gift=E9o0y7Rlfcfv2OQ1sSVCEm2HqWTlvBG_uUPQ_7tcOpI&utm_source=copy-link&utm_medium=social&utm_campaign=share

from my link log —
Jim Roskind’s C and C grammars.
https://blog.robertelder.org/jim-roskind-grammar/
saved 2026-03-10 https://

Everything I've written is my own, made by hand. I have used an LLM in this case, not to generate the text but to verify the payload. ;)
As usual, feedback is welcome. I have ADHD, mild dyslexia, and not a lot of free time. Grammar and spelling, especially typo checking, is always very much appreciated.
Edit:
There may be a few more mistakes than normal since I've kind of rushed it to hit while it's especially relevant.
Also... Open to formatting notes. I rushed that a bit too.

"Donald Trump now genuinely lives in a different reality, one in which neither grammar nor history nor the normal rules of human interaction now affect him. Also, he really is maniacally, unhealthily obsessive about the Nobel Prize."
Trump’s Letter to Norway Should Be the Last Straw - The Atlantic

🇺🇦 #NowPlaying on KEXP's #DriveTime
London Grammar:
🎵 Baby It’s You
#LondonGrammar
https://fernandoferreyra.bandcamp.com/track/london-grammar-baby-its-you-fernando-ferreyra-remix
https://open.spotify.com/track/1Yb6awhvnYL8W0PGk2sIbl

This is so niche and yet so relevant to my interests: "Kip is an experimental programming language that combines Turkish grammar rules with a type system. Case endings, vowel harmony, and other Turkish morphological features are an integral part of Kip's type-checking process."
https://github.com/kip-dili/kip/…

People:
Ramadan Karim!
ལོ་སར་དགེ་ལེགས!
新年好!
It's Ash Wednesday and the start of Ramadan. It's a Fire Horse year. Enjoy the confections and the meditations and the time with family, make all those precious networks strong and full of joy with whatever ritual grammar you prefer!

Like trying to understand a language by studying its alphabet, our increasingly precise measurements of music's neural architecture may capture its grammar, but they still miss how such experience emerges from form.

RE: https://hachyderm.io/@thomasfuchs/115922876937888251
Adding deliberate spellling, grammar and vocabulary mistakes to show you I'm human

Indian AI lab Lossfunk's prompting method lets LLMs generate Tulu language text without prior training; the method may expand to other low-resource languages (The Economic Times)
https://economi…

Paras Chopra’s Lossfunk gets AI models to speak Tulu through prompts, not training
Lossfunk, an AI lab founded by Paras Chopra, created a prompting method that helps large language models produce Tulu text without prior training. Using grammar rules and negative constraints, accuracy reached about 85%. The approach may help expand AI support for low-resource Indian languages without costly data collection or specialised training.

Wow, I finally have a functional grammar check in #emacs that seems like what I've been looking for.
https://stebalien.com/blog/grammar-tools-in-emacs/

Superb. "For too long, those fluent in the good grammar of civility have employed decorum to mask agendas of cruelty." Boom. #Mamdani

Is building an LLM inherently problematic? Not necessarily, but there's no good way to do it under capitalism. Is using an local LLM funding these evil companies? No. It's not.
Spelling and grammar checking is one of the few uses of LLMs that is not based on fundamentally failing to understand what an LLM actually is. A statistical model is gonna be *really good* at flagging things that are probably typos (low probability areas). There will be false positives, which is fine if you're actually paying attention...

Africa moved as many worlds. It still does.
— Not just rulers, but households, elders, children
— lives lived inside systems of memory, labor, belief, and power that did not require a single name.
So, to talk of Africa as a country is the residue of colonialism — what remains after empire leaves but its grammar stays.

{nplyr} has helper functions to work on nested dataframes: #rstats #datascience

A Grammar of Nested Data Manipulation
Provides functions for manipulating nested data frames in a list-column using dplyr syntax. Rather than unnesting, then manipulating a data frame, nplyr allows users to manipulate each nested data frame directly. nplyr is a wrapper for dplyr functions that provide tools for common data manipulation steps: filtering rows, selecting columns, summarising grouped data, among others.

from my link log —
pred_recdec: Predicated LL / recursive descent parser / grammar interpreter in Rust.
https://github.com/wareya/pred_recdec
saved 2026-02-08 https://

I was in the process of writing a short story when all this talk of #LLM spellchecking came up. So I wrote a story that you can't actually use an LLM spellchecker on because it breaks them:
#Writing #Fiction #SolarPunk

Just finished this...
https://hexmhell.writeas.com/the-fear
I've been working on a set of myths and folklore that exist within the context of a fantasy story I'm working on. This is one of them.
Feedback is always welcome, especially grammar and typos. Now back to editing a couple of other projects I've been working on.