Bob Flagg
@calcworks.bsky.social
Mathematician masquerading as a machine learning engineer. Currently focused on developing LLM applications to benefit people and the planet.
Just signed up for the General Strike: www.generalstrikeus.com
The General Strike
The General strike -the people united shall never be stopped. If we strike together we can make true real change. Sign the strike card today.
www.generalstrikeus.com
March 4, 2025 at 2:23 AM
Just signed up for the General Strike: www.generalstrikeus.com
Reposted by Bob Flagg
... “total shutdown” is planned for March 15...
Website for the General Strike:
generalstrikeus.com
OPPOSE! PLEASE REPOST!
Website for the General Strike:
generalstrikeus.com
OPPOSE! PLEASE REPOST!
The General Strike
The General strike -the people united shall never be stopped. If we strike together we can make true real change. Sign the strike card today.
generalstrikeus.com
February 16, 2025 at 10:25 PM
... “total shutdown” is planned for March 15...
Website for the General Strike:
generalstrikeus.com
OPPOSE! PLEASE REPOST!
Website for the General Strike:
generalstrikeus.com
OPPOSE! PLEASE REPOST!
Interesting ideas on designing agentic systems: Agents Are Not Enough (www.arxiv.org/pdf/2412.16241)
January 4, 2025 at 1:39 PM
Interesting ideas on designing agentic systems: Agents Are Not Enough (www.arxiv.org/pdf/2412.16241)
Hello, Hive Mind! Can you share advice on finding job opportunities using AI, NLP and LLMs for social good? Some topics that appeal are identifying and countering misinformation, democratizing knowledge access and addressing systemic bias. Salary is much less important than the focus of the work!
December 12, 2024 at 1:45 PM
Hello, Hive Mind! Can you share advice on finding job opportunities using AI, NLP and LLMs for social good? Some topics that appeal are identifying and countering misinformation, democratizing knowledge access and addressing systemic bias. Salary is much less important than the focus of the work!
Mask PII when interacting with an LLM API: arxiv.org/abs/2410.17127
PAPILLON: PrivAcy Preservation from Internet-based and Local Language MOdel ENsembles
Users can divulge sensitive information to proprietary LLM providers, raising significant privacy concerns. While open-source models, hosted locally on the user's machine, alleviate some concerns, mod...
arxiv.org
November 25, 2024 at 11:47 AM
Mask PII when interacting with an LLM API: arxiv.org/abs/2410.17127
Just got my copy and already finding valuable tools and insights for work projects. github.com/HandsOnLLM/H...
November 22, 2024 at 10:58 AM
Just got my copy and already finding valuable tools and insights for work projects. github.com/HandsOnLLM/H...
I'm finding Clue And Reasoning Prompting (CARP) (arxiv.org/pdf/2305.08377) surprisingly effective for curating labeled data for training relation extraction models.
arxiv.org
November 18, 2024 at 11:50 AM
I'm finding Clue And Reasoning Prompting (CARP) (arxiv.org/pdf/2305.08377) surprisingly effective for curating labeled data for training relation extraction models.