… also from Qwen today, Qwen-Image-Edit-2509, the "monthly iteration of Qwen-Image-Edit"!
@simonw
-
Qwen Audio Model Now Available: 70GB Weights for Local Deployment
By
–
This is really cool – you can try it out by signing into https://
chat.qwen.ai (with Google or GitHub) and selecting the audio icon The model weights are only ~70GB and that's before quantizing them down, so this one is going to be reasonably accessible to run locally -
Claude Artifacts limitations understanding state management constraints
By
–
Understanding the limitations of what can and cannot be built using Claude Artifacts and friends is devastatingly complicated though – the lack of support for storing state rules out a huge array of apps, only now users have to understand what the concept of "state" means
-
AI Search Modes: Useful Features vs Disappointing Overviews
By
–
It's so confusing how "AI mode" is genuinely useful and competes with ChatGPT GPT-5 Thinking for search, but "AI overviews" are still total trash
-
AI Labs Safety Measures Lack Transparency and Explanation
By
–
I've always assumed that the labs have steps in place to avoid that kind of thing happening, but none of them ever seem to want to explain what those steps are and how they work – which leaves me completely in the dark
-
Major AI Labs Lack Transparency on Critical Questions
By
–
I am eternally frustrated that I can't get a straight answer to questions like this one from ANY of the major AI labs
-
Science Fiction Predictions Technology Impact Gap Analysis
By
–
Saw a good TikTok about that yesterday, making the point that science fiction often predicts what future technology can do but rarely predicts the impact it will have
-
LLM Performance Optimization Through Lazy Import Strategy
By
–
I saw some nasty performance problems with my LLM tool with may plugins installed recently – turns out the solution was to switch to lazy imports inside functions instead (of the heavier dependencies at least)
-
LLM Plugins: Making Models Available Through Python Library
By
–
Yes, any plugin for LLM also makes those models available to the Python library Here's a bit of the documentation that covers that https://
llm.datasette.io/en/stable/pyth
on-api.html#models-from-plugins
… -
LLM Security: Untrusted Text and Prompt Injection Risks
By
–
I'd add another circle to that diagram for the permissions of anyone else who authored text that made it into the context – which often means untrusted external attackers since it's so easy to sneak in malicious instructions for a lot of LLM systems