Todd Toler retweeted
Good guide. And the AI labs need to stop making people like Simon (and, to a lesser extent, me) be the ones who explain how to use the modes that they release.
Come on, lab folks, you have an AI that can write documentation! And make explainers! And be a tutor! You can do this!
Here's my attempt at explaining what ChatGPT Work can actually do - it's a deeply confusing but extremely powerful tool with a whole lot of useful features that aren't available in regular ChatGPT simonwillison.net/2026/Aug/3…

ALT The better question then is what features does Work have that are missing from Chat? After extensive experimentation I think I’ve mostly figured that out: Options to use Luna and Terra in place of Sol A code execution environment with Internet access A headless Chrome browser A persistent filesystem shared between sessions The ability to publish ChatGPT Sites The ability to run sub-agent sessions with Sol, Luna, and Terra Scheduled prompt automations
Todd Toler retweeted
Today, I’m open-sourcing /fuck-cancer, an AI skill that helps patients and caregivers navigate cancer diagnosis and treatment and advocate for themselves and their loved ones.
Here’s what patients and caregivers have told me since I shared my mom’s story:
“You have to be a huge patient advocate. Ask questions and push for answers, biopsies, and proper testing.”
“I need help navigating difficult conversations and advocating for myself.”
“The volume of doctors, documents, and insurance paperwork can quickly become overwhelming.”
I built the skill to help with these problems. It creates and updates a practical brief with five sections:
1. Patient and care-team information for easy reference during calls
2. What to do next, limited to three specific actions
3. What we know, separating confirmed facts from what remains unclear
4. Medical terms explained in plain English
5. A care log with recent updates and decisions
It builds this brief from documents, and context you provide. When research is needed, it uses trusted sources such as the National Cancer Institute and the ClinicalTrials gov API.
I use it with ChatGPT/Codex and Claude Code to prepare for conversations and research. It can save the brief locally as a Markdown file or update a shareable Google Doc so the whole family can work from the same information.
📌 Get the free, open-source skill here:
github.com/petergyang/fuck-c…
If you find it useful, please ⭐ the repo and share it with someone going through this BS disease.
Todd Toler retweeted
I give you: the Curve of AI Adoption
The initial "aha" moment climbs quickly to "it can do anything," then at the first sign of trouble plummets into the chasm of garbage. Then comes the long, annoying climb to the plateau of earned competence.
Given how much I think about this post, it's one of the canonical pieces of the scholar-ready AI movement.
I wrote this post (The Collaborative Exoskeleton of AI Science) a month or so ago and then forgot to publish it! It’s where I build on my “missing mechanisms of the agentic economy” theme and apply it to the infrastructure of AI for science. Would love to know what real working scientists think about this. I hope the AI companies working on science think about it too ;-) open.substack.com/pub/asimov…
I’m thinking it’s time to rebrand my nickname from Solid State UX to Solid State Evidence. AI don’t care about my hover states and modals, yo.
open.substack.com/pub/simons…
AI doesn’t care about articles. It cares about tasks and chunks.
But in those chunks, it often loses the plot—like forgetting a paper was retracted.
This is a must read from @aarontay
open.substack.com/pub/aaront…
Great piece by Katie Parrott on how to keep your writing weird in the age of AI. Be your own goddamn arbiter of texture and give your erudite idiot scribe a style guide!
What does Bible criticism have to teach us about writing with AI? A lot, actually.
I wrote all about it for @every 👀
every.to/working-overtime/ho…
Todd Toler retweeted
What does Bible criticism have to teach us about writing with AI? A lot, actually.
I wrote all about it for @every 👀
every.to/working-overtime/ho…
Today’s platforms shine for human eyes. Tomorrow’s will shine for LLMs. Scrapeable, readable, reason-ready. The AI Gateway is opening — are we ready to step through? #ScholarlyPublishing #AIGateway
Todd Toler retweeted
PSA It’s a new era of ergonomics.
The primary audience of your thing (product, service, library, …) is now an LLM, not a human.
LLMs don’t like to navigate, they like to scrape.
LLMs don’t like to see, they like to read.
LLMs don’t like to click, they like to curl.
Etc etc.
Geek out on the history (and future!) of scholarly publishing infrastructure in my first ever podcast appearance.
podcasts.apple.com/us/podcas…
My side hustle as a Miami investigative reporter is officially underway. I contributed Best Manatee Viewing spot to the 2024 BOM. miaminewtimes.com/best-of/20…
Todd Toler retweeted
This is a game changer. You can use ChatGPT to transform equations to python functions.
Wish I had this 5 years ago.
Todd Toler retweeted
One thing I appreciate about Projekt Deal/@ColleenCampbe11 is the absolute focus on speeding the transition. No messing around with anti-hybrid. No trying to change where researchers should publish (e.g. commercial vs non-comm). Just get the hybrids to be fully OA over time.
Todd Toler retweeted
Please join our all-star April 12 panel for a discussion about "The Nelson Memo... Now What?" featuring Colette Bean (@APSPhysiology), @acochran12733 (@ASCO), @StevenInchcoom1 (@SpringerNature), @b_rockenbach (@yalelibrary) and me as @scholarlykitchn host. customer.sspnet.org/Portal/i…
Todd Toler retweeted
"it's still the gold standard. But it is a not easy-to-use tool. It's clunky. And as a result, we've allowed some ankle biters to come in around the edges." Does Clarivate see Elsevier's Scopus as an "ankle biter"? Or what else would this be referring to? seekingalpha.com/article/458…






















