惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

博客园 - 三生石上(FineUI控件)
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
月光博客
月光博客
博客园 - 【当耐特】
Hugging Face - Blog
Hugging Face - Blog
让小产品的独立变现更简单 - ezindie.com
让小产品的独立变现更简单 - ezindie.com
爱范儿
爱范儿
大猫的无限游戏
大猫的无限游戏
S
SegmentFault 最新的问题
博客园_首页
雷峰网
雷峰网
量子位
有赞技术团队
有赞技术团队
博客园 - 叶小钗
博客园 - 聂微东
V
V2EX
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
博客园 - 司徒正美
小众软件
小众软件
The Cloudflare Blog
阮一峰的网络日志
阮一峰的网络日志
Apple Machine Learning Research
Apple Machine Learning Research
Jina AI
Jina AI
人人都是产品经理
人人都是产品经理

Discourse Meta - Latest posts

Horizon: High Context Topic Cards I'd like to ask what this file /var/www/discourse/vendor/data/RT_sRGB.icm is used for? Discourse to Markdown Plugin How to verify a subdomain (mysite.discourse.group) in Google Search Console? Reader Mode Publishing WordPress gallery posts on Discourse Discourse User Feedback New user filter by custom field and contact Interact with discourse from Python? Why we can't type the assignee in the search of a post to assign - home screen app Redis Flushall Category-toggled one-touch move post Some sort of variable to eliminate duplicate text? Why did this plugin replacement fail? Add user to list modal often appears above the mobile viewport sceen Creating/Editing a post on mobile: let's discuss the 2026 Discourse experience Wp-discourse feature request - do not show comments with specific tag? Are there any good Chinese plugins? Discourse ID and 2FA Discourse MCP is here! Sample Forum to See Admin Features? I am unable to register for a free Discourse site Wikipedia Lookup Add text for /login (like js.create_account.disclaimer for /signup) How can i set disable Markdown & Default to Rich Text What's the background image size for the Welcome Banner? How do I enable Associated Accounts with 2FA? Hamburger toggle Support <span data-attribute> in the rich editor Cannot disable read-only mode on Free Plan
What happens to translations when LLM changes?
@RBoy RBoy · 2026-04-25 · via Discourse Meta - Latest posts
If I change the LLM do all the posts get retranslated? I was using a LLM hosted on groq, it was about 95% done when I started getting errors. After investigating it I realized that groq had deprecated the model I was using. So I setup a new model in groq and then updated the model parameters in discourse. I see that discourse is now using millions of tokens with the updated translation LLM every single day but the progress bar in the translations status page isn’t progressing at all (still stuck at 95%). So I’m trying to figure out what happens when the LLM parameters change? Does it start the translations all over again from scratch? If so is there any way to prevent it from doing that and just picking up from where it left off?