The CoT summary mostly what you’d expect — pages and pages of ideation about plausible nicknames and letter cycles, often nonsensically meandering. This is from the middle — imagine like 100 more pages of this stuff:
PROMPT ENGINEERING
-
AI Applications Approaching Performance Limits Against Specialized Engines
By
–
the wall is real, but the #application is still not near it's limit, if it can beat purpose built rules engines in value game?
-
Speculation on token probabilities and tokenization artifacts
By
–
Just a guess but maybe “ouches” and “unction” are strings just below some threshold of probability of following a space to earn a token? E.g. “unction” would be from function names (where “f” is swallowed by an unseparated prefix) and “ouch” often follows an open-quote or dash.
-
RepoChat: AI for GitHub Repositories
By
–
On another note, @lmarena_ai is rolling out RepoChat where you can select a public github repository and prompt a model to work with it
-
o1 Excels at Deep Reasoning and Creative Writing Tasks
By
–
o1 isn’t just for PhDs. It’s shockingly good at mastering writing styles that demand deep reasoning—not just logical arguments (ex: debate how maritime customs may nullify modern trade regulations), but also nailing rhythm and cadence in poetry, lyrics, puns, jokes, and scripts.
-
Switching model variants to use code interpreter for SVG download
By
–
It doesn’t have a code interpreter. When I did my previous post creating an SVG, I had to make the SVG in o1 and then switch the chat to 4o make it a downloadable file, and once you do that it won’t let you switch back because o1 doesn’t support code.
-
Comparing o1 model capabilities versus REPL
By
–
It isn’t important; this task isn’t practical at all; it’s just a compact illustration of the broadened class of tasks o1 can do vs earlier models, e.g. tasks that seem to require a guess-and-check loop with dozens of iterations REPL is still best for many real-world tasks
-
LLM struggles with counting and arithmetic despite code workarounds
By
–
Yeah, it’s actually not a hard problem in code — you just iterate over x values from 0 until you find one that works. What makes it remarkable here is just that counting letters and arithmetic are traditionally hard for LLMs and o1 claims to not be using tools/code
-
ChatGPT Plans Engineers Are Currently Using
By
–
Be honest: for the engineers that follow me, what ChatGPT plan are you currently on?
-
Creating a Chat UI Interface with Streamlit for RAG Applications
By
–
The Chat interface We create a UI using Streamlit to provide a chat interface for our RAG application. The code for this & all we discussed so far is shared in the next tweet! Check this out