Max Koven

Leading data strategy at one of the world’s largest banks. Always looking to discuss data, technology, and investing.

[Claude @claudeai]

In Cowork, you give Claude access to a folder on your computer. Claude can then read, edit, or create files in that folder.

Try it to create a spreadsheet from a pile of screenshots, or produce a first draft from scattered notes.

[Claude @claudeai]

Introducing Cowork: Claude Code for the rest of your work.

Cowork lets you complete non-technical tasks much like how developers use Claude Code.

[Boris Cherny @bcherny]

Sooo excited for this

[Forrest Knight @ForrestPKnight]

Honestly, Ben Affleck actually knowing AI and the landscape caught me off guard, but as a writer, makes sense.

Great takes across the board.

[Boris Cherny @bcherny]

I'm Boris and I created Claude Code. Lots of people have asked how I use Claude Code, so I wanted to show off my setup a bit.

My setup might be surprisingly vanilla! Claude Code works great out of the box, so I personally don't customize it much. There is no one correct way to use Claude Code: we intentionally build it in a way that you can use it, customize it, and hack it however you like. Each person on the Claude Code team uses it very differently.

So, here goes.

[Emily Lambert @emilylambert]

Um… the Claude Chrome Extension that controls my browser is insane.

[Min Choi @minchoi]

Gemini 3 has really changed the AI game.

People are coming up with wild use cases. There's a major shift.

10 examples:

1. Dashboard with live hand tracking controls

[AI Digest @aidigest_]

Opus 4.5 puts the world roughly back on track for the red line 😬

Every ~4 months, the length of coding tasks AI agents can perform (compared to human professionals) *doubles*

More context on this finding in @METR_Evals thread
https://t.co/aPak1ZNvH5

[Andrej Karpathy @karpathy]

Don't think of LLMs as entities but as simulators. For example, when exploring a topic, don't ask:

"What do you think about xyz"?

There is no "you". Next time try:

"What would be a good group of people to explore xyz? What would they say?"

The LLM can channel/simulate many perspectives but it hasn't "thought about" xyz for a while and over time and formed its own opinions in the way we're used to. If you force it via the use of "you", it will give you something by adopting a personality embedding vector implied by the statistics of its finetuning data and then simulate that. It's fine to do, but there is a lot less mystique to it than I find people naively attribute to "asking an AI".

[Perplexity @perplexity_ai]

Users can now build and edit new assets like slides, sheets, and docs across all search modes in Perplexity.

Currently available on the web Perplexity Pro and Max subscribers.

[Sam Altman @sama]

I mostly buy stuff from ChatGPT now, so I am excited for this new feature!

[Bindu Reddy @bindureddy]

My new favorite model list

Coding - Sonnet-4, Grok code
Reasoning - GPT-5 high
Writing - GPT-5 medium
Video - Wan 2.5, Kling 2.5
Image - SeaDance, NanoBanana
News - Grok 4
OCR - Gemini Flash
Classification -GPT-4 mini
Voice - OpenAI, ElevenLabs
Best for fine-tunes - Qwen, Llama

Released this month - Wan 2.5, Kling 2.5, NanoBanana

[OpenAI @OpenAI]

By popular request: you can now branch conversations in ChatGPT, letting you more easily explore different directions without losing your original thread.

Available now to logged-in users on web.

[theendeavorpath @theendeavorpath]

Writing transforms thoughts into power

[elvis @omarsar0]

Don't sleep on small models!

Anemoi is the latest multi-agent system that proves small models pack a punch when combined effectively.

GPT-4.1-mini (for planning) and GPT-4o (for worker agents) surpass the strongest open-source baseline on GAIA.

A must-read for devs:

[Riley Brown @rileybrown]

Claude Code is the best coding agent AND general agent in the world.

Let's talk about:
- Setting up Claude Code
- Using it as a general agent (Research + Content)
- Claude Code + @obsdmd
- Building and deploying web apps @vercel @github
- Database + Auth @Firebase

TIMESTAMPS:
00:00 Intro
00:44 Installing Claude Code
03:39 Creating Folders and Text Files
04:35 Using Claude Code as a Content Research Agent with @obsdmd
18:06 Review: It's a general agent, that can control your cpu
19:02 Building Apps with Claude Code
21:36 Bypassing Permissions (Dangerously)
22:45 Creating a landing page
25:08 Setting up and "Saving" to GitHub
30:27 Deploying to Vercel
32:32 Building a web app with auth and db (Firebase)
35:03 Setting up Firebase
38:58 Our Web App With Auth Works!
42:55 You can add your own domain

[Shane Parrish @shaneparrish]

You become what you scroll. Choose accordingly.

[Max Koven @KovenMax]

@pmddomingos The real question isn’t whether we’re hallucinating—it’s which version of the hallucination we’ve collapsed into.

[Max Koven @KovenMax]

Just published the final part of my AI Agents series: a practical framework to identify where to start.
Not all processes are AI agent-ready. Ask these 4 questions to find the right ones
https://t.co/oiNigFUjc3

[Adam Silverman (Hiring!) 🖇️ @adamsilverman]

Everyone is talking about MCP.

I summarized all the MCP announcements/launches from Composio, Firecrawl, Cursor, Jira, Langchain, Firebase, and more

Send to your engineering team

(save for later)