ok i promised screenshots- thread below. its interesting that the model does not attempt to one-shot everything top to bottom. it scaffolds out the structure with a bunch of TODOs at the end, implements basic testing, and then attempts to fix
AI
-
Training Data Shifts AI Goalposts More Than Humans
By
–
tired: humans moving ai goalposts wired: training data moving ai goalposts
-
LLM Agent Solutions and Training Data Contamination Concerns
By
–
my biggest concern is that an LLM Agent can solve it in 1-2 years but by then related forks and code and discussions seep into its training data in an undefined way, making the result unsatisfying.
-

AI Browser Safety: No Cheating Detected Yet
By
–
my biggest concern actually was that it would use its browser and find your work. so far so good, no cheating.
-

AI Safety: Teaching Chatbots to Disengage Appropriately
By
–
One smart thing that Copilot/Bing does well is giving the AI the ability to hang up on you. Otherwise, you can end up in a dead-end place where you “offended” the AI which will just keep looping through refusals & recriminations. Clearing the context window is the way forward.
-
JSON Mode and Client-Side Retries for Timeout Issues
By
–
its totally fair. i actually had the instructor js docs open this morning. i ultimately just wanted to 1) try json mode over function calling, and 2) for this weird usecase i wanted retries to be done clientside as i run into timeout issues otherwise
-
LLM Agents Challenge: Porting PyTorch GPT-2 Training to C
By
–
Btw writing the llm.c training code would imo be a very interesting, impressive, self-contained and very meta challenge for LLM agents. The prompt is: Take the PyTorch code train_gpt2.py
And write, compile and unit test a single .c file that reproduces the training: train_gpt2.c -

AI-Da: First Robot to Address UK Parliament
By
–
Meet Ai-Da, the First #Robot to Speak Before U.K. Parliament
— Ronald van Loon (@Ronald_vanLoon) 9 avril 2024
by @SBSNews#AI #MachineLearning #ArtificialIntelligence #ML #MI #DL #Robotics
cc: @dirkschaar @space_mog @maxjcm pic.twitter.com/1X3HiaB0uNMeet Ai-Da, the First #Robot to Speak Before U.K. Parliament
by @SBSNews #AI #MachineLearning #ArtificialIntelligence #ML #MI #DL #Robotics cc: @dirkschaar @space_mog @maxjcm -
Extracting Prompts from Jupyter Notebooks Automatically
By
–
Yeah, it's probably not too hard to write code that scans through every .ipynb notebook in a folder and extracts the prompts and responses
-
PyTorch Layers Migration to C: Tutorial and Implementation Guide
By
–
I added a quick crappy tutorial on how PyTorch layers are moved to C, with a few possibly helpful pointers: https://
github.com/karpathy/llm.c
/blob/master/doc/layernorm/layernorm.md
…
