for those who don't know, i use github issues as my CMS, but the actual blog with all my stuff is here https://
swyx.io/gemini-nano shipping @SvelteSociety sveltekit since the beginning
@swyx
-
Using GitHub Issues as CMS for SvelteKit Blog
By
–
-
Chrome Extensions and Prompt API Hackathon Idea
By
–
i def think somebody should run a little chrome extensions + prompt api hackathon…
-
Julius AI outperforms O3 on agentic dataviz task
By
–
bakeoff of o3 vs @juliusai on an agentic dataviz task o3 just shrugged julius just went to WORK amazing job @0interestrates @badphilosopher et al
-
LLMs as Platform Technology: Rejecting Update Frequency as Primary Metric
By
–
i reject the assumption but even granting the assumption, frequency of update is the completely wrong metric to optimize/decide on here. llms are platform tech and need to be on as low a level as possible or we will just have electron-but-llms all over again.
-
OS-level LLM integration instead of browser bundling
By
–
all of these are stupid tbh. bundling browsers with llms are stupid. distribute it with the os and let the browsers hook into them like a syscall.
-
Audio Support and SSML Importance Questions
By
–
they do have audio support? what is the imptnce of real ssml? (not familiar w it)
-
Chrome 138 Ships Gemini Nano Locally to 3.7 Billion Users
By
–
so Chrome 138+ onwards ships Gemini Nano for every user*, putting a local LLM in 3.7 billion monthly active users of Chrome wrote a personal guide today for building with Gemini Nano – mostly for me, might help you if you're not suuper strong at javascript or parsing google's…
-
Early Podcast Episode with Cursor AI Founders Captured
By
–
lowkey still kinda proud that we were the first podcast to feature @amanrsanger and @cursor_ai back in the day and we got the frozen in time oral history of the thinking back then when they were a baby company of 4 cofounders and 1 eng who just forked vscode hopefully valuable
-
High Quantity Item Summarization: Clustering and Ranking Multiple Small Items
By
–
high quantity item summarization (eg many small things -> clustered, ranked and summarized, rather than 1 big doc -> 1 summary)