The Stanford freshmen who want to rule the world . . . will probably read this book and try even harder
Can a book like this actually change anything? Or does the spotlight, as it always seems to, send more students racing to the place?
TechBrief — تازهترین اخبار فناوری
آخرین خبرها
Amazon’s new podcast strategy: Monetize everything
Amazon's podcasting business seems to have transformed over the past six months.
Butterflies are in decline across North America, a look at the Western Monarch
Comments URL: https://news.ycombinator.com/item?id=47914677
Points: 46
# Comments: 8
Show HN: AI memory with biological decay (52% recall)
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: 21
# Comments: 7
Sawe becomes first athlete to run a sub-two-hour marathon in a competitive race
https://www.letsrun.com/news/2026/04/15930-sabastian-sawe-sh...
Comments URL: https://news.ycombinator.com/item?id=47914350
Points: 120
# Comments: 75
I bought Friendster for $30k – Here's what I'm doing with it
Article URL: https://ca98am79.medium.com/i-bought-friendster-for-30k-heres-what-i-m-doing-with-it-d5e8ddb3991d
Comments URL: https://news.ycombinator.com/item?id=47914165
Points: 68
# Comments: 24
MoQ Boy
Article URL: https://moq.dev/blog/moq-boy/
Comments URL: https://news.ycombinator.com/item?id=47914161
Points: 15
# Comments: 1
What Tim Cook built
On the latest episode of Equity, we discuss how Apple has changed since Cook became CEO in 2011, and what challenges incoming CEO John Ternus will be facing.
Fast16: High-precision software sabotage 5 years before Stuxnet
Comments URL: https://news.ycombinator.com/item?id=47913855
Points: 79
# Comments: 22
Tomora’s Come Closer is an ecstatic love letter to 90s dance music
Before Coachella, Tomora wasn't on my radar at all. It's actually only by chance that I stumbled upon them - I opened the wrong stream because my TV was lagging like a MFer. I paused for a few moments, entranced by the two ethereal Nordic women banging on giant drums to a techno beat. I […]