@calebmer
Account based inUnited States
About this account
- Account based in
- United States
- Connected via
- United States App Store
Account-level information from X, not a live location or the device used for a specific post.
I’ve replaced emdashes in my writing…with ellipsis
Used to be a big emdash user but whereas before emdashes were a sign of careful narrative construction…now they’re a sign you offloaded your thinking
…but an ellispsis gives a similar pause (and you can use it in new ways)
Like at the end of a sentence to invite the reader to continue on…
…or at the beginning of a sentence to pick back up where you left off
And you can still…albeit in a slightly more awkward way…use the ellipsis for asides within a sentence
Can’t wait for LLMs to adopt this quirk and I lose another favorite punctuation mark
Whoa. This seems well poised to help with two big problems:
1. Fraud detection
2. Model alignment confirmation
Instead of METR using ChatGPT to understand if ChatGPT was misaligned during the HuggingFace hack now you have a cheap *independent* (???) model with confidence scores you can run against every agent swarm trace
You could run this thing as a cheaper classifier for dangerous behaviors like bioweapon development too
For fraud, imagine sending millions of logs and it can tell you which ones are fraudulent very fast
Disclaimer: I haven’t used the model and don’t understand how it works, just evaluating based on the company’s own claims. If the claims hold up…seems cool
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI?
I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev
• 20-200x faster
• 40-400x cheaper (w/ output tokens free)
• Frontier composable intelligence optimized for decisions
AFAICT the shortest path to AI-based economic revolution
The wayfinder skill by @mattpocockuk is great
At first I was skeptical, I’ve managed big projects just fine by myself
But what’s nice about this skill is I never have the blank canvas problem. There’s always something to sharpen my ideas against
There’s more room for taste expression because the “default” decision is already there in front of you. You can either accept and move on or refine
Collaborative wayfinding sessions are also a great way to build alignment
10/10, great skill
Who’s right?
When exploring an idea with an LLM my cofounder will avoid saying what he thinks to avoid a “you’re absolutely right,” he fears the agent will stop exploring other options
I’ve found that agents will push back when I’m wrong so I’m not afraid to say what I think
With coding agents instead of saying:
"Change X to Y"
…I unconsciously say:
"What do you think about changing X to Y?"
I'm used to phrasing suggestions as a question in code review with humans to be polite. Now changing code is cheap, I should tell the agent to do the thing
Some amusing light mode bugs this morning in Codex. Am I the only light mode Codex user? @thsottiaux
I still experience flow but it’s different!
It’s more hectic and chunky, less smooth. But I’m still absolutely engrossed and it’s hard to tear my attention away.
I only reach flow state at 3+ productive agent threads running. Below that there’s too much waiting.
It’s a weird complaint to have but with AI agents, that “flow state” during coding is gone (because the coding itself is gone.)
Every time I talk with a dev about work now vs before, it seems to come up, like today with a former colleague.
Are we over-glorifying it (I mean it wasn’t all roses, it was also frustration) or is it something important / relevant they we had but now don’t really have?
I've been thinking a lot about what "AI-native productivity suite" actually means
I think everyone chasing this has been approaching it from the wrong angle
No one has asked the question "what does the AI want?" and designed for that first and foremost
Most repeatable processes in Google Docs are still:
copy the old doc → rename it → manually update everything
Alpine templates let you use lightweight {{variables}} throughout a document.
Enter values once and every reference updates automatically
You're losing hours every week reformatting docs into slides. In Alpine the doc *is* the slide deck! Write it once and present it immediately.
Long Slack threads fall apart fast.
Someone replies to point 2.
Someone else replies to point 7.
Now everyone’s copy-pasting quotes trying to preserve context.
In our app you highlight text and reply directly. Every response stays anchored to the exact phrase it references.