Here are other notes I've made about exploring LLMs for code over the past couple of years https://
simonwillison.net/series/using-l
lms/
…
LLMS
-
Exploring LLMs for Code Development Notes and Resources
By
–
-
Using LLMs Responsibly: Code Review and Quality Assurance
By
–
As with so many things involving LLMs, combining with deep existing expertise is important – to responsibly use them for code you need to be great at reading code, code review, considering edge-cases, automated testing and extensive QA Good code review skills go a long way here
-
Code Generation: AI’s Self-Verifying Use Case
By
–
I actually think code is one of the most responsible use-cases for it, because you get a weird form of fact checking for free: if it hallucinates methods that don't exist you find out the moment you actually try to run the code and it fails Much easier to verify code than prose!
-
Structured generation improves LLM performance and consistency
By
–
This blog post on the effect of adding "structured generation" on the performances and consistency of LLMs was a good read Thanks a lot for that @willkurt @remilouf and @clefourrier
-
32K Context Window with Backend Optimization Tricks
By
–
Currently 32K, but we do some clever tricks on the backend that should make it feel near-infinite when you're using it.
-
Microsoft LLM, OpenAI Stack Overflow, AI Tools and Jobs Updates
By
–
Top stories in AI today: -Microsoft training massive in-house LLM
-OpenAI partners with Stack Overflow
-Studio-quality audio in seconds with AI -Study: Teachers can’t detect AI writing
-6 new AI tools & 4 new AI jobs Read more: http://
therundown.ai/p/microsofts-n
ew-chatgpt-competitor
… -
Daily Content on Python, Data Science, Machine Learning, and MLOps
By
–
That's a wrap! If you are interested in any of these below topics: – Python – Data Science – Machine Learning – Data Analysis – LLMs – MLOps Find me → @Sumanth_077 I'm sharing daily content over here.
-
ChatGPT 4 Performance Improvements Noticed by Users
By
–
Estoy de acuerdo en que he notado a ChatGPT 4 notablemente más rápido.
-
LMSYS Chatbot Arena model naming issues escalate
By
–
model naming on the lmsys chatbot arena is getting out of hand
-
GPT-4 vs New Model: Matplotlib Code Generation Comparison
By
–
Le he pedido a GPT-4 y a uno de los nuevos modelos que me hicieran el código en Matplotlib para dibujar una palmera, un coche y a la Mona Lisa. Tratándose de Matplotlib y resultados generados en código ambos modelos son bastante buenos, ¿pero cuál es mejor?