Back
Jason Wu
Load previous page…
Update cursor to 0.41, now you can have composer on side panel, and checkpoints are available
See similar todos

No replies yet

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/…
See similar todos

No replies yet

publish newseltter
See similar todos

No replies yet

It seems vercel.app is blocked by GFW
See similar todos

No replies yet

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

No replies yet

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
See similar todos

No replies yet

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

No replies yet

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

No replies yet

update symbol search on client & server #cappy
See similar todos

No replies yet

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

No replies yet

Go camping ⛺️
See similar todos

No replies yet

Number of flights I've taken in recent years ✈️
See similar todos
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.
See similar todos

No replies yet

fine-tune gpt4 for analysis #cappy
See similar todos

No replies yet

have some fun?
See similar todos

No replies yet

Today's reading arxiv.org/pdf/2305.20050
See similar todos

No replies yet

do you have gpt-o1 access yet? openai.com/index/introducing-…
See similar todos

No replies yet

replace company info api with ticker search #cappy
See similar todos

No replies yet

get market data from alphavantage #cappy
See similar todos

No replies yet