nicognaw
Re:OpenAUTH: Universal, standards-based auth provider
on Wednesday December 18, 2024 @06:59AM (#42449786)
OpenAuthJs is literally a hono app.
Re:The obscure social media app beloved by China's tech scene
on Friday May 17, 2024 @10:27PM (#40396076)
Users in these kind of platforms usually do welcome English posts according to some experience with Xiaohongshu, but registering an account from outside is challenging.
Re:Run llama3 locally with 1M token context
on Wednesday May 01, 2024 @01:07AM (#40219708)
If you got random tokens on Apple Silicon Macs, you should check your stderr for Metal’s error code, like 5 for out of metal memory. Metal lets you use half of your unified memory as metal memory.
Re:Andrej Karpathy: Intro to Large Language Models [Video]
on Thursday November 23, 2023 @01:08AM (#38389880)
Andrej made the micrograd video after the code was released a couple years later. As someone who takes learning neural networks as a hobby, I really want to see him make videos about the llama.c project.
Re:Major Outage Across ChatGPT and API
on Wednesday November 08, 2023 @09:46AM (#38191052)
Azure OpenAI
Re:Clash, a tool to break China's Great Fire Wall, is Deleted in GitHub
on Friday November 03, 2023 @02:04PM (#38132572)
As learned by the community, they leaked their personal information from emails used in git commits
Re:GPT-4 Update: 32K Context Window Now for All Users
on Friday November 03, 2023 @01:57PM (#38132476)
+1, the OpenAI official playground & the new fine-tuning UI are really useful stuff, but surprising enough, I don't find open source versions.
Re:New: LangChain templates – fastest way to build a production-ready ...
on Friday November 03, 2023 @12:31PM (#38131100)
Why would I use drag-and-drop UIs to replace one of my favorite things, coding, when I use infrastructure as code stuff to replace a cloud console panel, FastAPI to generate OpenAPI documents, and even D2-lang to draw graphical diagrams?
Re:Hysteria is a powerful, fast and censorship resistant proxy
on Friday October 27, 2023 @12:32AM (#38034723)
In some US states where TikTok is banned, this can be used to access it.
Re:Jina AI Launches First Open-Source 8K Text Embedding, Rivaling OpenAI
on Wednesday October 25, 2023 @10:55PM (#38021154)
Jina AI itself is also a great framework to expose APIs from deep neural net models and deploy them to Kubernetes clusters, which I think is very promising, but they didn't get as much hype as I predicted that they deserved.
Re:OpenTelemetry at Scale: Using Kafka to handle bursty traffic
on Sunday October 22, 2023 @10:47PM (#37981054)
Signoz is too good at SEO.
Early days, I looked up otel and observability stuff, and I always saw Signoz articles on the first screen.
Ask HN: Why is AI companies not using AI support chatbot?
I found that OpenAI, Anthropic, and Cohere all use intercom, and none of them have AI support chatbots enabled. Smaller companies like Jina AI use Crisp.If AI chatbots are really productive, why are companies that developed them not using them?
Re:Train Your Own Private ChatGPT Model for the Cost of a Starbucks Co...
on Thursday June 01, 2023 @09:43PM (#36159855)
TL;DR: Cheap GPU cloud with alpaca-LoRA
Re:Ask HN: Which React framework for a new project?
on Monday April 10, 2023 @10:40PM (#35520092)
Maybe a bit extreme, but I am going to use Remix and only Remix for my new side projects.
Re:AI powered realtime fluid silulations are here
on Saturday April 08, 2023 @04:00AM (#35491487)
I'm actually very excited to see AI applied in games in ways other than AI agents.
Re:Show HN: Atmos – Everything you need to create color palettes
on Wednesday March 29, 2023 @09:06AM (#35356671)
As a developer, I'd like a tool to help me design the color scheme for my IDE, and I'm curious if this one can do that.
Re:Generative AI is good at cooperating with people and bad at full au...
on Wednesday March 29, 2023 @02:42AM (#35353496)
Prompt engineering, in my opinion, could be considered "semantic programming."
Re:Generative AI is good at cooperating with people and bad at full au...
on Wednesday March 29, 2023 @02:21AM (#35353339)
Since LLMs generate words one by one, you can only determine whether the next word has a high probability. Some ideas occurred to me earlier, like applying prompt engineering to evaluate if the model is confident about the contents to be generated.
Like "Please reply T if you are confident about the text that you are going to generate, and F if you are not".
But if this could be done by architecting the neural networks, they would perform much better.
Re:LLMs and GPT: Some of my favorite learning materials
on Tuesday March 28, 2023 @04:05PM (#35347041)
I'm learning the basics of transformer from Andrew Ng's courses, your post seems to make me learn it faster. Thanks!
Re:ChatGPT can in fact ask you questions
on Sunday March 19, 2023 @02:44PM (#35222140)
Why not? The actual work that language models do is to complete the conversation. It doesn’t actually answer questions, it just tries to make the text look real.