Heykuki News

TopNewBestAskShowJobs
TopNewBestAskShowJobs
1.
80.1 % on LoCoMo Long-Term Memory Benchmark with a pure open-source RAG pipeline
3 points
ViktorKuz
6 months ago
discuss
2.
I built an open-weights memory system that reaches 80.1% on the LoCoMo benchmark
2 points
ViktorKuz
6 months ago
2 comments
3.
Show HN: Memory System Hitting 80.1% Accuracy on LoCoMo (Built in 4.5 Months) (github.com/vac-architector)
2 points
ViktorKuz
6 months ago
discuss
4.
Hi, I'm Viktor.I wasn't a programmer. I didn't build apps. I didn't write code
1 point
ViktorKuz
5 months ago
1 comment
5.
80.1 % on LoCoMo Long-Term Memory Benchmark with a pure open-source RAG pipeline
1 point
ViktorKuz
5 months ago
discuss
6.
Show HN: Change the model. Same output. The pipeline decides. VAC Memory System
1 point
ViktorKuz
6 months ago
discuss
7.
They Say AI Will Replace Programmers. I Think AI Will Mass-Produce Them Instead (github.com/vac-architector)
2 points
ViktorKuz
6 months ago
2 comments
8.
Show HN: I built an AI that remembers everything and learns from mistakes (github.com/vac-architector)
2 points
VAC-AGI
10 months ago
1 comment
9.
Show HN: VAC Memory – 80.1% LoCoMo accuracy vs. Mem0's 68% (github.com/vac-architector)
2 points
ViktorKuz
6 months ago
discuss
10.
VAC Memory System – SOTA RAG (80.1% LoCoMo) Built by a Handymen Using Claude CLI (github.com/vac-architector)
1 point
VAC-AGI
6 months ago
2 comments
11.
Show HN: MCA-Entity Coverage as a Memory Retrieval Gate (github.com/vac-architector)
1 point
ViktorKuz
6 months ago
1 comment
12.
Show HN: VAC — AI with Human-Like Hierarchical Memory that Learns and Improves (github.com/vac-architector)
1 point
VAC-AGI
10 months ago
discuss