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