Because my last two posts about ChatGPT have done more than 7 million impressions combined. Almost 50,000 likes total. Looks like a lot of people are looking to learn. So, if you reconsider, here are those posts again:
LLMS
-
Claude AI Demonstrates Enhanced Self-Awareness Compared to GPT-3
By
–
Compare to GPT-3, Claude (a new model from @AnthropicAI
) has much more to say for itself. Specifically, it's able to eloquently demonstrate awareness of what it is, who its creators are, and what principles informed its own design: -
Encoding Mistakes in Retrieval-Augmented Models
By
–
or prompts, e.g. in retrieval-augmented models. but only if you call your `.encode()` wrong 🙂
-
Using AI to Write a Complete Book: Workflow and Experiment
By
–
It could help you create an outline and then you could have it help fill the outline in piece by piece. I could see a workflow here, sure. In the next few weeks I’m going to try to make it write a whole book just for giggles.
-
Text as Complete Human Experience Description in GPT Models
By
–
Big takeaway from the GPT paradigm is that the world of text is a far more complete description of the human experience than almost anyone anticipated.
-
Fine-tuned models achieve quality results with minimal steps
By
–
This is 50 but at 35 it was nice already indeed, esp with finetuned models I can get rly good results with low step count, sometimes even 10 and short prompts
-
LangChain Implements Conversational Agent Interface
By
–
Conversational Agent One pain point we heard was people trying to get agents to work in a conversational interface Although not perfect, we now have an implementation of this h/t @brunotorious for driving a lot of this, + @nfcampos & @andrewgleave https://
langchain.readthedocs.io/en/latest/modu
les/memory/examples/conversational_agent.html
… -
OpenAI API Update: Logprobs and Agent Tool Improvements
By
–
v0.0.58 Add generation reason and logprobs to @OpenAI response – @diwanksingh Add @OpenAI logit bias param – @benderville bug fixes (h/t @shivanshug11 , @brain_exe_ai ) And a bunch of Agent & Tool improvements! So many we can't list them all in this tweet ->
-
Writers Must Lead the ChatGPT Conversation, Not Ignore It
By
–
A lot of writers have avoided talking about the AIs, myself included, for a long time But ChatGPT is happening, with or w/out us After thinking hard about it, I decided I'd rather be a leader here and help people navigate this situation rather than sit back and watch it unfold.
-
ChatGPT and Other AI Writing Tools Comparison
By
–
ChatGPT is the most capable right now, but I like some other tools by http://
Mem.ai and http://
Jasper.ai and the Notion writing assistant as well https://
openai.com/blog/chatgpt/