The underlying language model picks one! They’ve gotten really good at reasoning
LLMS
-
ChatGPT Will Look Like a Toy in Six Months
By
–
The craziest thing about ChatGPT In 6 months, it’s going to look like a toy
-
GPT-003 excels over 002 in zero-shot style imitation with Jar Jar Binks
By
–
It’s better than 002, particularly at following style directions given in zero-shot. Try asking for something technical “in the speaking style of Jar Jar Binks.” In 002 you just get a slight accent without even a “mesa”, but in 003 you see similes about Gungan swamps.
-
ChatGPT disappoints user, stifles prompt writing joy and experimentation
By
–
I’m done with ChatGPT for a while. It’s sucked the joy out of prompt writing for me. Default writing quality is easy to achieve but hard to improve; opaque front-end and high temperature prevent the sort of casual analysis and experimentation that made fall in love with GPT-3.
-
Evidence for real prefix: consistent format and current date
By
–
The reason I think it’s a real prefix is that 1) it’s in the same consistent, bizarre format every time (note date style) and 2) it contains the current date, information a pure LLM could not possibly have, and which would thus make sense to insert into a prompt prefix.
-
Virtual Agents and Conversational Interfaces Report Coverage
By
–
what does « virtual agent or conversational interface » cover in the report?
-
LangChain v0.0.35 Release: Documentation Improvements and New Features
By
–
LangChain v0.0.35 Doc improvements @HunterGerlach Fix typing of parameters, flagged by @fcampeot
Expose more parameters for the q&a chains, suggest by @johnjnay Add a `.clear()` method for memory, @shobith and @andrewgleave Support -1 for max_tokens, @BruceHammer -
Training LLMs for Personalized Education Systems
By
–
Train LLM on every published text of a given subject, enable user feedback, deploy into a for-profit education system. This can be done for all subjects, from physics to ethics.
-
AI Achieves Stunning Advance in Computer Code Writing
By
–
#AI learns to write computer code in ‘stunning’ advance
#RuleoftheRobots https://
science.org/content/articl
e/ai-learns-write-computer-code-stunning-advance#.Y5VC5wLum1g.twitter
… -
AI Systems Confident Yet Frequently Wrong Reliability Concerns
By
–
it does know a lot, but the danger is that it is confident and wrong a significant fraction of the time