This is a site that maps the references on Gary Overacre's 1980s UNIX Magic
poster to short write-ups with sources. I posted an earlier version about a
year ago [1]. Since then I rewrote some of the annotations, added
deep-linking to individual markers and a frame/sidebar view, gave the site a
terminal-style redesign, and fixed historical inaccuracies (daemon etymology,
nroff origin, B language vs. Multics, etc.).
Contributions and comments welcome; each marker is a GitHub issue.
site: https://unixmagic.net
[1] https://news.ycombinator.com/item?id=43019136
Comments URL: https://news.ycombinator.com/item?id=47916769
Points: 3
# Comments: 0
I put this together (with Claude) as a semi-gamified way for folks to learn about startup equity. Take a look, and share your scorecard :)
Comments URL: https://news.ycombinator.com/item?id=47915274
Points: 15
# Comments: 7
Can a book like this actually change anything? Or does the spotlight, as it always seems to, send more students racing to the place?
Amazon's podcasting business seems to have transformed over the past six months.
Most RAG setups fail because they treat memory like a static filing cabinet. When every transient bug fix or abandoned rule is stored forever, the context window eventually chokes on noise, spiking token costs and degrading the agent's reasoning.
This implementation experiments with a biological approach by using the Ebbinghaus forgetting curve to manage context as a living substrate. Memories are assigned a "strength" score where each recall reinforces the data and flattens its decay curve (spaced repetition), while unused data eventually hits a threshold and is pruned.
To solve the "logical neighbor" problem where semantic search misses relevant but non-similar nodes, a graph layer is layered over the vector store. Benchmarked against the LoCoMo dataset, this reached 52% Recall@5, nearly double the accuracy of stateless vector stores, while cutting token waste by roughly 84%.
Built as a local first MCP server using DuckDB, the hypothesis is that for agents handling long-running projects, "what to forget" is just as critical as "what to remember." I'd be interested to hear if others are exploring non-linear decay or similar biological constraints for context management.
GitHub: https://github.com/sachitrafa/cognitive-ai-memory
Comments URL: https://news.ycombinator.com/item?id=47914367
Points: 60
# Comments: 30