HyperWrite mobile is still a bit behind web, but we’re improving it every week.
@mattshumer_
-
Build Your Ideas Using LLMs as Your Development Partner
By
–
Decide what you want to build and just go for it. Ask LLMs for help when you need it. This is the way.
-
Claude excels at generation and self-prompting capabilities
By
–
Claude is incredible at this. Very valuable. Especially if you’re using Claude for generation as well. It knows how to prompt itself quite well 🙂
-
Evaluating AI Outputs: Subjective Preferences and Domain Expertise
By
–
Subjective: depends on the use-case… sometimes I’ll just go with my preference, or ask a few people to rate outputs. Domain specific: ask smarter LLMs or domain experts!
-
Using Claude Haiku for cost-effective prompt stuffing
By
–
If it’s under 200k tokens and I can afford it, I’m using Claude Haiku and stuffing it all in the prompt.
-
AI Development Stack: Local Setup with Cloud Compute
By
–
My couch. MacBook Pro. Runpod for compute. Axolotl for training. OpenAI Playground and Anthropic Console for prompt engineering. Sometimes PromptKnit.
-
Complete AI Development Stack: Runpod, Axolotl, and Prompt Engineering
By
–
My couch. MacBook Pro. Runpod for compute. Axolotl for training. OpenAI Playground and Anthropic Console for prompt engineering. Sometimes PromptKnit.
-
AI Models Learn Faster With Less Training Data
By
–
Doubt it. As models get smarter, less data will be needed to teach them new things. So if today, it takes millions of examples to teach it a new language, a couple years from now, it may only need a few thousand.
-
Adding Example Inputs Outputs Improves Prompt Performance
By
–
Try adding example inputs/outputs to the prompt!