HackerTrans
TopNewTrendsCommentsPastAskShowJobs

decorner

no profile record

Submissions

OrgForge: The Next Step in Enterprise AI Simulation

machinebrief.com
3 points·by decorner·11 dni temu·0 comments

Agent memory is leaving the cute "remember this" demo phase

self.md
6 points·by decorner·12 dni temu·0 comments

[untitled]

1 points·by decorner·22 dni temu·0 comments

Ask HN: What AI memory system or workflow are you working on?

1 points·by decorner·24 dni temu·0 comments

How AI memory systems break at scale

tenureai.dev
3 points·by decorner·24 dni temu·1 comments

AI Memory Fails Spectacularly: 95% Error Rate Unveiled

machinebrief.com
4 points·by decorner·w zeszłym miesiącu·2 comments

Show HN: LLM memory without context bleed; 100% precision vs. <10% vector search

tenureai.dev
4 points·by decorner·w zeszłym miesiącu·1 comments

Why Vector Search fails at LLM memory (and a benchmark to prove it)

github.com
3 points·by decorner·w zeszłym miesiącu·0 comments

LLM memory systems benchmark: high recall near-zero precision for tested systems

arxiv.org
4 points·by decorner·w zeszłym miesiącu·0 comments

comments

decorner
·20 dni temu·discuss
When your router ships with IPv6 default on, this makes sense
decorner
·30 dni temu·discuss
New overlord, same as the old overlord.
decorner
·w zeszłym miesiącu·discuss
I think it's referring to this article: https://zamin.uz/en/technology/205592-ai-memory-proves-ineff...
decorner
·w zeszłym miesiącu·discuss
Benchmark: https://github.com/tenurehq/precisionmembench - 89 cases measuring retrieval precision indendepently of any LLM. Paper if you want to deep dive on the tech: https://arxiv.org/abs/2605.11325