Simon Willison’s Newsletter
Subscribe
Sign in
Home
Archive
About
Latest
Top
Discussions
Llama 3.1, now available in LLM
The best available openly licensed model is now competitive with GPT-4o and Claude 3.5 Sonnet
Jul 24
•
Simon Willison
10
Share this post
Llama 3.1, now available in LLM
simonw.substack.com
Copy link
Facebook
Email
Note
Other
1
GPT-4o mini, LLM 0.15, sqlite-utils 3.37 and building a staging environment
Plus Mistral NeMo, Codestral Mamba and Llama-3-Groq-Tool-Use Models
Jul 19
•
Simon Willison
6
Share this post
GPT-4o mini, LLM 0.15, sqlite-utils 3.37 and building a staging environment
simonw.substack.com
Copy link
Facebook
Email
Note
Other
Imitation Intelligence keynote at PyCon 2024
And: Give people something to link to so they can talk about your features and ideas
Jul 15
•
Simon Willison
7
Share this post
Imitation Intelligence keynote at PyCon 2024
simonw.substack.com
Copy link
Facebook
Email
Note
Other
Open challenges for AI engineering
Plus a flurry of tiny tools built using Claude 3.5 Sonnet
Jul 8
•
Simon Willison
4
Share this post
Open challenges for AI engineering
simonw.substack.com
Copy link
Facebook
Email
Note
Other
June 2024
Building search-based RAG using Claude 3.5 Sonnet, Datasette and Val Town
The new Claude 3.5 Sonnet is now the best available LLM
Jun 24
•
Simon Willison
10
Share this post
Building search-based RAG using Claude 3.5 Sonnet, Datasette and Val Town
simonw.substack.com
Copy link
Facebook
Email
Note
Other
1
Language models on the command-line
Plus Datasette Studio, prompt injection against GitHub Copilot Chat and more
Jun 19
•
Simon Willison
7
Share this post
Language models on the command-line
simonw.substack.com
Copy link
Facebook
Email
Note
Other
Thoughts on the WWDC 2024 keynote on Apple Intelligence
Plus Claude's personality, Qwen 2 model censorship, OpenAI Voice Engine and more
Jun 10
•
Simon Willison
10
Share this post
Thoughts on the WWDC 2024 keynote on Apple Intelligence
simonw.substack.com
Copy link
Facebook
Email
Note
Other
Accidental prompt injection against RAG applications
Plus notes on Microsoft Recall and more
Jun 6
•
Simon Willison
10
Share this post
Accidental prompt injection against RAG applications
simonw.substack.com
Copy link
Facebook
Email
Note
Other
May 2024
Training is not the same as chatting: ChatGPT and other LLMs don't remember everything you say
Plus notes from PyCon and LLM support for GPT-4o and Gemini Flash
May 29
•
Simon Willison
10
Share this post
Training is not the same as chatting: ChatGPT and other LLMs don't remember everything you say
simonw.substack.com
Copy link
Facebook
Email
Note
Other
2
ChatGPT in 4o mode doesn't have the new voice and image features yet
Plus Gemini Flash and PaliGemma from Google I/O
May 16
•
Simon Willison
6
Share this post
ChatGPT in 4o mode doesn't have the new voice and image features yet
simonw.substack.com
Copy link
Facebook
Email
Note
Other
GPT-4o, a new version of LLM and more thoughts on slop
Notes on GPT-4o, OpenAI's latest model release
May 14
•
Simon Willison
8
Share this post
GPT-4o, a new version of LLM and more thoughts on slop
simonw.substack.com
Copy link
Facebook
Email
Note
Other
1
LLM slop, datasette-secrets, llm-evals, gpt2-chatbot and a whole lot more
Plus 28 links and 19 quotes from the past two weeks
May 8
•
Simon Willison
10
Share this post
LLM slop, datasette-secrets, llm-evals, gpt2-chatbot and a whole lot more
simonw.substack.com
Copy link
Facebook
Email
Note
Other
1
Share
Copy link
Facebook
Email
Note
Other
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts