ICYMI: We launched new cross-environment AI observability with enterprise-grade open-source LLM hosting — available across all AI assets and environments. Not able to join live? Check out the on-demand recording from our virtual launch event with @decisionleader and @nvidia
GENERATIVE AI
-
OpenAI May No Longer Want ChatGPT Paid Subscriptions
By
–
I think Open AI really does not want me to pay for ChatGPT anymore
-
Using AI to pipe and combine existing code for new tools
By
–
I have a lot of fun piping in existing code and having it make changes – adding small new features for example like here, where I gave it a bunch of my existing code and had it combine that to produce a new tool https://
simonwillison.net/2024/Mar/30/oc
r-pdfs-images/#ocr-how-i-built-this
… -
Text transformation and summarization over generative AI focus
By
–
Yeah, I think the "generative" piece is somewhat distracting – for me the most interesting applications are mostly related to transformation – feeding in a larger amount of text and having it answer questions based on that, restructure it, summarize it etc
-
Using LLMs to Solve Coding Problems Quickly
By
–
This one is a particularly good illustration of working in conjunction with an LLM to very quickly solve a small but interesting coding problem https://
simonwillison.net/2024/Mar/22/cl
aude-and-chatgpt-case-study/
… -
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!
-
Using ChatGPT to Build C Extensions for SQLite
By
–
I use it for code all the time – here are some of my most relevant notes: https://
simonwillison.net/2024/Mar/23/bu
ilding-c-extensions-for-sqlite-with-chatgpt-code-interpreter/
… and -
Ransomware Protection and Cyber Resilience in GenAI Era
By
–
New! Readiness within Reach! Empowering Ransomware Protection and Cyber Resilience in the Age of GenAI! See http://
bit.ly/ReadinessinRea
ch
… As the @RSAConference 'Where the World Talks #Security ™' hits full swing, the stage is set for a deep dive across the many changes -
HyperWrite excels in writing assistance with custom LLaMA 3 model
By
–
The use-case for @HyperWriteAI is different than ChatGPT + Claude. Those are best for solving coding/reasoning problems. If you're looking for writing assistance, research, creative help, etc., this is where HyperWrite shines. Subscribe to both. It's worth it. Matt Shumer (@mattshumer_) LLaMA 3 70B is live on @HyperWriteAI! A custom version I've been working on for weeks. – writes more like a human than any other model – can access real-time info Crushing every other model, including GPT-4, in user preference tests. 🤯Seriously, look at the writing quality: — https://nitter.net/mattshumer_/status/1787650529067175968#m
→ View original post on X — @hyperwriteai, 2024-05-07 15:08 UTC
-
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