This is the single most offensive thing a company has ever done to me.
Confluent have just published a podcast congratulating themselves on how great their episodes have been over the past year & I’ve been totally erased. It’s as though I never existed.
Cheap shot CFLT. 😞
I'm putting together a book + database of every idea & framework from MFM
Need someone to help me do this by listening to every ep and extracting all the good stuff.
Paid project. Should last ~1 month.
Requirement:
- must have that dog in 'em
Apply:
https://t.co/37N4E6Xmj7
Want to implement chain-of-thought reasoning in your text-to-SQL tool to help guide the SQL query generation? One way is to provide few-shot examples demonstrating CoT. @langchain makes this a piece of cake. (1/4)
Kor (https://t.co/P4j6zbTIXf) now features integration with LangChain. Kor's aims to help extract structured data from text using LLMs. If you take Kor for a spin, and have ideas or complaints please share (https://t.co/DSst98v6P5). I would love to hear back!
We are getting closer to “Her” (part 2!)
Conversationally do anything with emails, using LLM chaining & few-shot prompting for tool use (@langchain inspired)
This is now realtime (ish), thanks to #OpenAI gpt-3.5-turbo
🔈 on for voice realism!
🧵
I am very excited to announce I have been successful in installing and operating a full ChatGPT knowledge set and interface fully trained on my local computer and it needs no Internet once installed.
There are no editors and there is no censorship.
I am using Alpaca (https://t.co/tJeAa5jYxN) from Stanford and Dalai Lama.
The training model cost about $530 to build locally yet has the abilities of GPT 3.5.
The software is free and open source and I am working on preconfigured packages for anyone to have local training and access to a LLM GPT AI.
This model is now in a live connect with all of my other AI systems and the results have been absolutely stunning.
I will be writing more about this soon.
But today know, you will own your own AI and it will only answer to you.
I just upgraded to macOS Ventura and my beloved window manager Divvy has finally kicked the bucket. What’s the best *simple* macOS window manager? 98% of the time I’m running “set to full size” or “set to 50% (left/right/up/down)”
The following code will tell you if a user's phone is in low power mode, with 100% accuracy, immediate feedback and no network requests.
This strategy loads a 16x16 video made of just 2 black frames as a base64 (text) source. This means no load time for the test asset, which has a total inline weight of 2.4kb.
Put this video immediately inside the body tag and hide it with CSS (base64 src pasted in this thread):