imaurer
Joined 8 years ago
Karma
257
Submissions
55
Member since
Aug 13
Recent submissions
Comment · 1 month ago
Faster, cheaper, and maybe better. The article explains the last part.
Comment · 7 months ago
vibe compliance
Comment · 2 years ago
Have a bunch of Makerile commands (pbcopy-api, pbcopy-ui, pbcopy-curr) that use some mishmash of git ls-files, grep, xargs tail -n +1 piped into pbcopy.
Kitchen sink command: pbcopy-all: git ls-files | xargs tail -n +1 | pbcopy
Works like a charm in Q2 2024.
I’m sure this will be a very solved problem by 2025.
Comment · 2 years ago
“ Finding effective documentation, information, and training is likely to get harder, especially in specialised topics where LLMs are even less effective than normal.”
Who needs documentation with Claude and pbcopy?
Comment · 2 years ago
I'm excited for the Michael Lewis version of the Rust library ecosystem.
Comment · 2 years ago
Groq will soon support function calling. At that point, you would want to describe your data specification and use function calling to do extraction. Tools such as Pydantic and Instructor are good starting points.
I am collecting these approaches and tools here: https://github.com/imaurer/awesome-llm-json
Comment · 2 years ago
Currently, LLM models are not state of the art at Named Entity Recognition. They are slower, more expensive and less accurate than a fine tuned BERT model.
However, they are way easier to get started with using in context learning. Soon, they will be cheaper and probably faster enough too that training your own model will be a waste of time for 95% of use cases (probably higher because it will unlock use cases that wouldn’t break even with the old NLP approaches from a value perspective).
This is why I am tracking LLM structured outputs here:
https://github.com/imaurer/awesome-llm-json
And created an autocorrecting pydantic library that could be used for Named entity linking:
Comment · 2 years ago
R2 support for egress $$ reasons?
Comment · 2 years ago
How'd they get both Chainsmokers?
GitHub: https://github.com/imaurer
Twitter: https://twitter.com/imaurer
LinkedIn: https://www.linkedin.com/in/ianmaurer