This is 100% one of the most exciting things about LLM’s. A whole generation is going to have a much better relationship with math, science, and programming because they can get the help they need in a way that makes sense to them.
@officiallogank
-
Stripe API design influenced OpenAI architecture decisions
By
–
Because @gdb built the stripe API and then started OpenAI so went with the design that worked well there.
-
OpenAI Python SDK 1.0 Release: Beta Testing Now Available
By
–
Exciting news for @OpenAI devs: we are close to a 1.0 release of the OpenAI Python SDK . You can test the beta version of 1.0 today, we would love to get your early feedback!
-
SF friends seek Cruise and Waymo autonomous vehicle invite codes
By
–
Do any of my SF friends have a Cruise or Waymo invite code?
-
XGBoost Community Celebrates Major Milestone with Global Contributors
By
–
Congrats to the XGBoost community and the contributors around the world who enabled this
-
Fine-tuning Function Calling Reduces Token Costs Improves Reliability
By
–
Fine-tuning for function calling is a big win! Great work making this happen, developers can now: – save token costs by fine-tuning the functions and then removing them at inference time
– improve the reliability of function calling output -
VC-backed companies increasingly adopt open source strategies
By
–
Many companies raising rounds / VC backed are also building open source to begin with which certainly wasn’t the case 5-10 years ago.
-
Fine-tuned Models and API Access Limitations Explained
By
–
It’s likely a fine-tuned model, hence why it’s not accessible when using your own API key.
-

San Francisco’s Path to Paradise Through Strategic Decisions
By
–
If San Francisco gets 5-6 key decisions right in the next 10 years, it is going to be a paradise. We are so back!
-

OpenAI Ships API Dashboard Update for Better Model Usage Clarity
By
–
Good news for @OpenAI devs: we just shipped an update to the API usage dashboard which should help make it more clear which models are driving usage and should generally be more reliable. Image credit to @mhmazur since I can't share my usage.