Alex W

Founder of @distillnote_ | 📸 Capturing the world one snap at a time | 🐶 Dog lover

[Simon Willison @simonw]

GPT-5.5 may not be in the official OpenAI API... but it's available via the apparently approved-of Codex API backdoor

So I used that to make these pelicans (default and xhigh)! https://t.co/kIx2wnhpqD

[Alex W @AlexWoe89]

@simonw the left one chose the hard mode .. crossing legs 😂

[Alex W @AlexWoe89]

@aryanlabde true

[Alex W @AlexWoe89]

@awwstn Where can I send my money to get this chrome extension? ty

[Alex W @AlexWoe89]

@ClaudeDevs Resetting limits when weekly limit is being reset in 1 hour for most subs feels very generous….

[Alex W @AlexWoe89]

@felixrieseberg @bcherny where to send my money?

[Boris Cherny @bcherny]

Opus 4.7 uses more thinking tokens, so we've increased rate limits for all subscribers to make up for it. Enjoy!

[Thariq @trq212]

Managed Agents is the first 'agent in the cloud' API that has the right mix of simplicity and complexity.

Implementation details like how you manage a sandbox are abstracted, but you have a lot of control over the actual execution of the model.

[Claude @claudeai]

Introducing Claude Managed Agents: everything you need to build and deploy agents at scale.

It pairs an agent harness tuned for performance with production infrastructure, so you can go from prototype to launch in days.

Now in public beta on the Claude Platform.

[Alex W @AlexWoe89]

@Tnimbus @claudeai nope, read the article

[shira @shiraeis]

anthropic’s really got me doing palliative care for claude

[Boris Cherny @bcherny]

Mythos is very powerful, and should feel terrifying. I am proud of our approach to responsibly preview it with cyber defenders, rather than generally releasing it into the wild.

Model card here: https://t.co/HjhknJcRKQ

[Alex W @AlexWoe89]

5/ The real question: how long until the rest of the field catches up?

My guess, longer than people think. General SOTA ≠ elite vulnerability research.

What’s your take?

[Alex W @AlexWoe89]

1/ Anthropic just dropped something big, and most of us won’t get access to it.

Project Glasswing + Claude Mythos Preview.

A thread 🧵

[Anthropic @AnthropicAI]

Introducing Project Glasswing: an urgent initiative to help secure the world’s most critical software.

It’s powered by our newest frontier model, Claude Mythos Preview, which can find software vulnerabilities better than all but the most skilled humans.
https://t.co/NQ7IfEtYk7

[Alex W @AlexWoe89]

4/ And that’s exactly why it’s gated.
A model that can find zero-days better than top humans is a dual-use risk. You don’t just ship that publicly.

Frustrating? Yes. Makes sense? Also yes.

[Alex W @AlexWoe89]

@mal_shaik at least it acknowledged it was wrong

[Corey Ganim @coreyganim]

Karpathy's "second brain" concept in 60 seconds:

1. Three folders (raw, wiki, outputs). That's the whole architecture.
2. One CLAUDE.md schema file tells the AI how to organize everything.
3. Dump your bookmarks, notes, and articles into raw/. Don't organize them.
4. One prompt: "Compile a wiki from raw/ following CLAUDE.md." Walk away.
5. Ask questions against your wiki. Save answers back. It compounds.
6. Monthly health check catches errors before they stack.

No Obsidian or complex plugins. Just desktop folders and a schema file.

Full walkthrough + free skill that builds it for you in 60 seconds in the article below.

[Anthropic @AnthropicAI]

You can read a detailed technical report on the software vulnerabilities and exploits discovered by Claude Mythos Preview here: https://t.co/AgU6ltV2qW