an agent in every cup
collecting bits & bobs about building alliances with other intelligences
an agent in every cup
OmniQuery: Contextually Augmenting Captured Multimodal Memories to Enable Personal Question Answering
SOCIAL MEDIA TITLE TAG
Mirror, mirror… what we often misinterpret when we talk about large language models.
Source: Betley, Tan, Warncke et al, “Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs”: emergent-misalignment.com
#ai #llm #gpt #claude #artificialintelligence... See more
tiktok.comFearing AI will take their jobs, California workers plan a long battle against tech
Khari Johnsoncalmatters.org
An agent can be thought of as a logical wrapper around an LLM, allowing us to add several features to our AI systems, primarily:
- Tool usage, such as calling APIs for info, executing code,
- Internal thoughts over multiple generation steps
- Ability to use various tools and reasoning steps to answer more complex queries.
- Parallel agents can go and complete
James Briggs • LLMs Are Not All You Need | Pinecone
2501.13956
arxiv.orgDeep Learning is Not So Mysterious or Different
arxiv.org
Programming as Theory Building
Peter Naur's "Programming as Theory Building" discusses programming as a knowledge-building activity, emphasizing the importance of tacit knowledge, collaboration, and effective documentation in developing and maintaining software systems.
ratfactor.com