prototype insight cards #cappy

add firestore security rules #cappy

Productivity decrease during travel 💔need to schedule more focus time to get things done

run into China Open, lots of tennis players are staying at the hotel 🎾

very generic learning algorithm + lots of compute + lots of data

Update cursor to 0.41, now you can have composer on side panel, and checkpoints are available

Switch the editorial pipeline to use o1, with the same data collected, result is much better structured, and highlights more important stuff #contentcreation www.blockrundown.com/article/…

publish newseltter

It seems vercel.app is blocked by GFW

Landing 🛬 at Beijing and checking if I can still access GitHub, almost lost my streak due to time zone change 😅

Publish new episode of "Next In AI", about the foundational Google paper revealing the secret of o1 open.spotify.com/episode/3Lcu… [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters] #nextinai

Publish AI generated paper reading podcast "Next In AI", this episode is about "Let's verify step by step" underlying OpenAI's o1 model: open.spotify.com/episode/0mmG… Is this helpful? #nextinai

Read [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](arxiv.org/pdf/2408.03314)

do entitlement process and get near real-time data from nasdaq #cappy

update symbol search on client & server #cappy

Read [Extrinsic Hallucinations in LLMs](lilianweng.github.io/posts/20…)

Go camping ⛺️

Number of flights I've taken in recent years ✈️

my impression with o1 so far: it requires more "thinking" from the human as well. To get the best result, I find myself writing a well thought through "letter" to the model vs. rapid fire "sms" to a simpler model without the reasoning capabilities. And yes, I create that "letter" with a simpler model during the initial "exploration" phase.

fine-tune gpt4 for analysis #cappy