Nathan Cooper
ncoop57.bsky.social
Nathan Cooper
@ncoop57.bsky.social
I'm a nerd (https://nathancooper.io).

The world can be ugly and cruel to the most innocent. Consider donating to help children suffering from one of the worst things: http://thorn.org/donate
Pinned
As R&D staff @ answer.ai, I work a lot on boosting productivity with AI. A common theme that always comes up is the combination of human+AI. This combination proved to be powerful in our new project ShellSage, which is an AI terminal buddy that learns and teaches with you. A 🧵
At @answerdotai, we integrate @stripe into lots of projects. Every time, I found myself doing the same dance: create product, create price, create checkout session. Then hunting docs for parameters for each. So we built FastStripe, a self-documenting Stripe SDK that's easy to use!
July 23, 2025 at 6:03 PM
🚀 ShellSage 0.1.0 has arrived, much to the relief of shell-challenged humans everywhere!

Introducing sagent mode: now you can manipulate files by simply asking instead of learning actual commands.

pip install shell-sage and embrace your laziness with ssage --mode agent today!
March 20, 2025 at 5:10 PM
🎉 ShellSage 0.0.8 is now live!

New features:
• Query logging to SQLite using `--log` flag (because who doesn't love a good paper trail?) 🗃️
• Better tmux history handling (for when your terminal has an existential crisis) 🛠️

Get it now: pip install shell_sage
February 22, 2025 at 6:22 PM
Reposted by Nathan Cooper
With @bclavie.bsky.social and @ncoop57.bsky.social, we tried to answer two questions:

- Can an instruction-tuned ModernBERT zero-shot tasks using the MLM-head?
- Could we then fine-tune instruction-tuned ModernBERT to complete any task?

Detailed answers: arxiv.org/abs/2502.03793
It's All in The [MASK]: Simple Instruction-Tuning Enables BERT-like Masked Language Models As Generative Classifiers
While encoder-only models such as BERT and ModernBERT are ubiquitous in real-world NLP applications, their conventional reliance on task-specific classification heads can limit their applicability com...
arxiv.org
February 10, 2025 at 6:13 PM
🤖 ShellSage v0.0.7
What's new? (besides our growing disdain for user error)
• Added --v flag because apparently you need to know these things
• Fixed config issues because reading docs is hard
• Better tmux support (you're welcome)

Upgrade your terminal's IQ:
`pip install shell-sage`
February 1, 2025 at 3:29 PM
Had another magical moment with shell sage! I was fixing a repo issue and asked shell sage for the issues. Then used my quick commit alias (which uses shell sage), and it automatically added “Resolves #22” to the commit since it could see them in my terminal! 🤓🤓
February 1, 2025 at 3:04 PM
Found an amazing new usecase for shellsage's command mode: autogenerating git commits 🤓!

I aliased `qc` to `git diff --cached | ssage --c please generate a concise git commit for these changes` and shellsage will enter the command I need with a great commit msg!
January 19, 2025 at 6:47 AM
Reposted by Nathan Cooper
🎉 ShellSage v0.0.6 is now available!

New features:
• Add new command mode for automatically inserting the correct command into your terminal
• Add Support for OpenAI Compatible Providers

Various bugs squashed too!

github.com/AnswerDotAI/...
December 28, 2024 at 5:33 PM
🎉 ShellSage v0.0.6 is now available!

New features:
• Add new command mode for automatically inserting the correct command into your terminal
• Add Support for OpenAI Compatible Providers

Various bugs squashed too!

github.com/AnswerDotAI/...
December 28, 2024 at 5:33 PM
Reposted by Nathan Cooper
Thanks to my two co-leads: @nohtow.bsky.social , @bclavie.bsky.social , & the rest of our stacked author cast: @orionweller.bsky.social, Oskar Hallström, Said Taghadouini, Alexis Gallagher, Raja Biswas, Faisal Ladhak, @tomaarsen.com , @ncoop57.bsky.social , Griffin Adams, @howard.fm , & Iacopo Poli
December 22, 2024 at 6:12 AM
Interesting use of Shell Sage to see all of the panes that helped me out today. Had two panes: one for setting up Caddy configuration, and one for running a FastHTML app. Was getting a 303 error that I didn't understand, and so asked Shell Sage what was happening and gave it the entire context🤓
December 21, 2024 at 6:12 PM
Reposted by Nathan Cooper
🎉 ShellSage v0.0.5 is now available!

New features:
• ShellSage defaults to seeing entire tmux scrollback history
• Important settings configurable via ~/.config/shell_sage/shell_sage.conf
• System info now included in prompts

pip install shell-sage

github.com/AnswerDotAI/...
GitHub - AnswerDotAI/shell_sage: ShellSage saves sysadmins’ sanity by solving shell script snafus super swiftly
ShellSage saves sysadmins’ sanity by solving shell script snafus super swiftly - AnswerDotAI/shell_sage
github.com
December 19, 2024 at 4:43 PM
Reposted by Nathan Cooper
Post credits easter egg:

Hey did you wonder what if we trained a bigger model? Where would that take us?

Yeah, us too.

So we're gonna train a "huge" version of this model in 2025. We might need to change the y-axis on this graph…
December 19, 2024 at 4:45 PM
Reposted by Nathan Cooper
I'll get straight to the point.

We trained 2 new models. Like BERT, but modern. ModernBERT.

Not some hypey GenAI thing, but a proper workhorse model, for retrieval, classification, etc. Real practical stuff.

It's much faster, more accurate, longer context, and more useful. 🧵
December 19, 2024 at 4:45 PM
Reposted by Nathan Cooper
I feel the need for speed.
December 13, 2024 at 9:56 PM
🎉 ShellSage v0.0.5 is now available!

New features:
• ShellSage defaults to seeing entire tmux scrollback history
• Important settings configurable via ~/.config/shell_sage/shell_sage.conf
• System info now included in prompts

pip install shell-sage

github.com/AnswerDotAI/...
GitHub - AnswerDotAI/shell_sage: ShellSage saves sysadmins’ sanity by solving shell script snafus super swiftly
ShellSage saves sysadmins’ sanity by solving shell script snafus super swiftly - AnswerDotAI/shell_sage
github.com
December 19, 2024 at 4:43 PM
Reposted by Nathan Cooper
I can now run a GPT-4 class model on my laptop

(The exact same laptop that could just about run a GPT-3 class model 20 months ago)

The new Llama 3.3 70B is a striking example of the huge efficiency gains we've seen in the last two years
simonwillison.net/2024/Dec/9/l...
I can now run a GPT-4 class model on my laptop
Meta’s new Llama 3.3 70B is a genuinely GPT-4 class Large Language Model that runs on my laptop. Just 20 months ago I was amazed to see something that felt …
simonwillison.net
December 9, 2024 at 3:19 PM
Reposted by Nathan Cooper
Reposted by Nathan Cooper
🎉 New FastHTML Gallery entry thanks to @carlolepelaars.bsky.social

HTMX example demonstrating click to load new table row 😃
December 6, 2024 at 9:38 PM
Reposted by Nathan Cooper
Thanks to HTMX + fh-frankenui the implementation is very simple!

Check it out :D

gallery.fastht.ml/split/dynami...
FastHTML Gallery
A gallery of FastHTML components showing common patterns in FastHTML apps, including chat bubbles, cascading dropdowns, interactive charts, etc.
gallery.fastht.ml
December 7, 2024 at 7:17 PM
Reposted by Nathan Cooper
🎉 New FastHTML Gallery entry!

Dynamic dropdown with:
✅ Search box in dropdown
✅ Input for users to add additional values
December 7, 2024 at 7:16 PM
New version of shellsage (0.0.4)! now available on Pypi:

- Add support for OpenAI models
- Remove action mode
- Add ability to configure shell sage with a configuration file

pip install shell_sage
ssage Hi --provider openai --model gpt-4o-mini
December 7, 2024 at 8:14 PM
Reposted by Nathan Cooper
As R&D staff @ answer.ai, I work a lot on boosting productivity with AI. A common theme that always comes up is the combination of human+AI. This combination proved to be powerful in our new project ShellSage, which is an AI terminal buddy that learns and teaches with you. A 🧵
December 5, 2024 at 8:27 PM
Reposted by Nathan Cooper
So how was my first week back at Google?

- PaliGemma2 was openly released
- DeepMind openly released GenCast weather forecast (in a GCP bucket 🙈)
- Genie 2 🧞world model was announced

This team ships 🔥🚀 Let's go!
December 6, 2024 at 2:15 PM