Introducing the Poe API v2 for developers! First, this now lets any bot on Poe to query any other bot for free and use the output as input. Developers do not have to pay anything for this; any messages used are covered under users' normal free messages on Poe. (thread)
CODE
-
Stanford’s Spellburst Tool Streamlines Coding Art Creation Process
By
–
Coding art is a time-consuming, complicated process. Stanford scholars sought to make this process seamless through a new tool called Spellburst.
-
Fast SDXL Inference with JAX on TPU v5e
By
–
Fast SDXL Inference with JAX on TPU v5e Amazing how fast anyone can generate 4 1024×1024 resolution SDXL images in under 5 seconds, for free: https://
huggingface.co/spaces/google/
sdxl
… -
Non-conventional paths to AI engineering careers matter
By
–
In the AI realm, diverse experiences matter, and there is no “conventional path” anymore. Former @Microsoft and @GoogleDeepMind engineer, @gordic_aleksa built his amazing portfolio through competitive programming, hackathons, implementing ideas from coding books, and attending
-
Neural Network Architecture Growth During Agent Lifetime
By
–
This reminds me of backprop NEAT, but the difference is here, the neural network architecture develops and grows during the lifetime of the agent!https://t.co/0V3BC5Cu9v pic.twitter.com/gMqYUyvRZZ
— hardmaru (@hardmaru) 4 octobre 2023This reminds me of backprop NEAT, but the difference is here, the neural network architecture develops and grows during the lifetime of the agent! https://
blog.otoro.net/2016/05/07/bac
kprop-neat/
… -
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 -
High-Quality LLM Watch and Reading List with Transformer Blueprint
By
–
A high-quality LLMs watch/reading list here: https://
gist.github.com/rain-1/eebd5e5
eb2784feecf450324e3341c8d
… Contains videos/lectures/articles that do great job at explaining LLMs and GPT models including our "Transformer Blueprint" article 🙂 -
Roll Out New Model Versions Without Downtime or Code Changes
By
–
You can roll out new versions of the model you're running, so you can change versions without downtime and without having to edit your code.
-
Replicate Deployments: Control, Visibility, and Model Management
By
–
It's easy to run models on Replicate, but what if you need to keep a model switched on, roll out a new version, or monitor how it's performing? You can now create a deployment to give you more control and visibility.
-
Groq Hiring Infrastructure Software Engineer for Services and Tools
By
–
Join @GroqInc as an #Infrastructure #SoftwareEngineer and help maintain a wide array of services and tools cutting across all #SoftwareEngineering, including assembler, compiler, systems/runtime, user libraries, and machine learning applications. https://
groq.com/careers/?gh_ji
d=4192706003
…