Any theories on what caused that leap since March? Likely to be new image generation?
@simonw
-
Qwen 3 30B Models Show Promise Over Recent Alternatives
By
–
Good but not exceptional based on my first impressions – I'm more excited about the recent Qwen 3 30B models
-
ChatGPT Sharing Dialog UX Issues and User Confusion
By
–
I wrote about what went wrong with ChatGPT's sharing dialog, and why I think it's reasonable for people to be confused by what looks at first glance like a very clear checkbox description
-
XBai o4 Model Missing from Chinese Documentation
By
–
They link to https://
wenxiaobai.com from their GitHub README but it's all in Chinese and when I translated the model picker it didn't mention the XBai o4 model -
XBai o4: New 32.8B Open Weights LLM from MetaStone AI
By
–
Here are my notes on XBai o4, the latest 32.8B open weights LLM to come out of an AI lab in China, this time from new-to-me MetaStone AI
-
Conversational Prompting Patterns for High Quality AI Solutions
By
–
Yeah I think there's a lot to be said for conversational prompting patterns, where you guide it towards a high quality solution though carefully asking questions in a sequence that fills its context with the right information
-
Distributed Unique Primary Keys Architecture Design
By
–
They wrote about how that works here https://
code.flickr.net/2010/02/08/tic
ket-servers-distributed-unique-primary-keys-on-the-cheap/
… -
Distributed ID Generation: Database Strategy and Flickr Technique
By
–
Leave it to the database, they're really good at that You can also use the Flickr trick if you need it – have multiple ID issuing databases, for example one serving even numbered IDs and one serving odd numbered IDs – then they can create new IDs independently of each other
-
DSPy Evaluation Strategies for AI Systems
By
–
I haven't tried DSPy myself yet (beyond reading docs) so I'm not in a position to answer that – if you can figure out how to effectively write evals for it I imagine it could work really well
-
GPT-4o-mini 2024 Model Paper By Same Authors
By
–
That paper is by the same authors – it's about gpt-4o-mini-2024-07-18 though which is a year old now