> very low-end hardware

iPhone 17 Pro outperforms AMD’s Ryzen 9 9950X per https://www.igorslab.de/en/iphone-17-pro-a19-pro-chip-uebert...

In single threaded workloads, still impressive

"Carrot: The Musical" in the Carrot weather app, all about the AI and her developer meatbag, is on point.

> Sadly teams is not accessible to it right now. MS Power Automate sadly does not enable forwarding the content of chats. Unlike with emails or calendar appointments.

In the spirit of CLIs being easy on your tokens:

https://pnp.github.io/cli-microsoft365/cmd/teams/chat/chat-g...

Use the JSON responses for full detail including e.g. reactions.

Composio, behind the blog post, offers "Enterprise" pricing, and has no Teams examples. A stat HN ignores: 85% of SMBs are on M365, not Google Workspace and Slack.

You can pick winners and losers in a segment early, by whether they treat M365 as a first class platform or pretend it doesn't exist. Check for the "Continue with Microsoft" button or support for OIDC not just SAML+SCIM, as well as examples for Teams.

This isn't just true for YC classes, holds true for unicorns. Compare Anthropic's "Claude in Excel" and "Claude in PowerPoint" instead of in Google Docs or Sheets, and guess which firm has a better grasp of how business works outside the valley. And yeah, Claude in Chrome works in Edge (and the lack of just renaming and posting Claude in Edge for normals to find is an ANTHROP\C miss).

> I think this may sound smart and counterfactual to common knowledge as a layman, but to anyone who regularly goes outdoors in extreme conditions, this article and experiment is horseshit.

LLM slop in a nutshell.

If today's LLMs could shake their annoying verbal tics, they might be indistinguishable from Malcolm Gladwell.

Turing didn't go far enough. The next level is the Gladwell Test: Indistinguishable from a human who is persuasively confused.

Because a machine wrote it, not a human.

I’m useless at recognizing AI writing sometimes; so, if this is that, email the mods and ask them to flag it off the site. (Explaining why you view it as AI writing will save a round or two of reply.) I’m all for what the twins are doing but AI writing should be purged here.

Yep:

Now, here’s the fun bit for gear geeks like us: it’s not cosplay; it’s rigorous historical reconstruction. … Their rule is strict: materials must be 100% natural—wool, silk, cotton, fur, and leather.

No rule against LLMs, or for rigorous human writing.

The twins didn't write this.

let's get carried away.

`uv run` a .py with inline script metadata has all the deps installed and your script running in a venv while poetry is still deciding to resolve...

uv, yes*, but really PEP 723:

https://peps.python.org/pep-0723/

* disclosure: We are a commercial client of astral.sh

This is cool! I ended up also inventing my own syntax to place at the top of one-off scripts to specify deps. (For single-file Python scripts, vs one with a full project dir that has pyproject.toml) I will adopt this instead.

It’ll probably be a game changer for scripts, yes. Writing “portable” Python scripts was a nice exercise, though (and will be, for a while).

Sounds a lot like vim/emacs modelines. This is neat for standalone scripts.

Instructive, with a rewarding repo for your time.

Or just don't sound like LinkedIn or freshman papers.