Currently exploring and writing about AI
Joined March 2011
- Tweets143
- Following397
- Followers134
- Likes87
I am running this course tomorrow in collaboration with @nikillinit 's team. Come join us!
If you're running a healthcare company, where does it make sense to build agents?
Today it seems like people want to just throw the amorphous "agent" term at everything, but maybe not all of those workflows are good fits. Workflows that ARE good for agents:
1) You spend a ton of hours on the task
2) There are pretty clear rules that you could write out
3) You can measure performance with a specific metric
4) Downside risk is low to test
1
64
Congrats on the launch. Exited to try it!
I’m excited to share what @drewregitsky and I have been working on over the past few months: @boxesdotdev! If you're coding with Claude Code or Codex, it's time to move your development from localhost into the cloud. 1/11
1
132
good product skills is landing the product at the right spot between tech possibilities, use case. and user psychology/habits.
How Anthropic’s product team moves faster than anyone else
I sat down with @_catwu, Head of Product for Claude Code at @AnthropicAI, to get a peek into their unprecedented shipping pace, how AI is changing the PM role, and how to be the right amount of AGI-pilled.
We discuss:
🔸 How Anthropic’s shipping cadence went from months to weeks to days
🔸 The emerging skills PMs need to develop right now
🔸 Why you should build products that don't work yet—then wait for the model to catch up
🔸 Why a 95% automation isn't really an automation
🔸 Cat’s most underrated AI skill (introspection)
🔸 What Cat actually looks for when hiring PMs now (hint: it's not traditional PM skills)
Listen now 👇
youtu.be/PplmzlgE0kg
1
88
👀 what we know about the Anthropic Mythos unauthorized access situation so far:
- Apr 7: Anthropic announces Claude Mythos Preview ("too dangerous for public release"). Same day, a private Discord gets in.
- Bloomberg broke it Apr 21. Everyone else is rewriting.
- Vector: a 3rd-party contractor's legit creds + Mythos endpoint URL guessed from Anthropic's naming convention.
Possibly bootstrapped off a prior Mercor breach.
- The Discord runs GitHub-monitoring bots to surface unreleased model endpoints.
bloomberg.com/news/articles/…
130
The demo is usually the easy part.
The real test is what happens when the page changes, the login expires, the input is messy, or the next step is not obvious.
That is where most automation breaks.
58
1. LLM models itself can actually be a great product. jasper.ai copy.ai and the OG chatgpt.com @ChatGPTapp
1
14
Had a great weekend hacking on tokify.onrender.com with @ptrln @ametaheuristic @osama_ @richardgong @yadapruksachatk
@OpenAI X @spc Hackathon
3
14
625
What AI newsletter do you read? Looking for something with a good information-noise ratio. Mostly want to subscribe to open-source projects, major model updates, and new papers. I care less about "BigCo doing an AI thing". Haven't found anything good yet.
124
1. LLM based ReAct agent inspired many innovative projects including @babyAGI_ @ChattGptPro and many implementation in @langchain.
But how does it work internally? Here's an example code walk through in ~150 lines of code.
We are in the beginning phase of incorporating AI everywhere. Sharing a collection of common AI application patterns, tools, models, and research papers to help more people get started hacking!
github.com/tedcheng/ai-hacke…
1
141
1. One of my new year goals is to catch up on various new technologies. AI is one not to be missed. A 🧵 to document my learning and look for new suggestions.
1
102
2. Over the holidays I worked through @jeremyphoward's FastAI 2022 course. It’s hands down the best deep learning course to get started and it’s completely free!
1
27