HackerTrans
TopNewTrendsCommentsPastAskShowJobs

brgsk

no profile record

Submissions

The empty corner in brain-to-text

brgsk.xyz
3 points·by brgsk·10 hari yang lalu·0 comments

Agent Memory: An Anatomy

brgsk.xyz
40 points·by brgsk·2 bulan yang lalu·18 comments

How Not to Run a Company

brgsk.xyz
2 points·by brgsk·3 bulan yang lalu·0 comments

How Not to Run a Company

brgsk.xyz
5 points·by brgsk·3 bulan yang lalu·0 comments

Show HN: Memv – Memory for AI Agents

github.com
4 points·by brgsk·3 bulan yang lalu·3 comments

Memory Is the Residual of Surprise

brgsk.xyz
2 points·by brgsk·4 bulan yang lalu·0 comments

comments

brgsk
·26 hari yang lalu·discuss
[dead]
brgsk
·2 bulan yang lalu·discuss
[flagged]
brgsk
·2 bulan yang lalu·discuss
20
brgsk
·2 bulan yang lalu·discuss
fair - repetition and density got in the way in places. cleaning that up for next.

the zet description sounds interesting - test-time compute at storage time especially.

is the repo public somewhere? github.com/vessenes/zet 404s for me.
brgsk
·2 bulan yang lalu·discuss
thanks for reading
brgsk
·2 bulan yang lalu·discuss
separate tradeoff worth naming - do you want "memories" available within session vs after the conversation has ended? that was what i was trying to convey in this paragraph
brgsk
·2 bulan yang lalu·discuss
good catch - the example is sloppy. the real issue is lost-in-the-middle on long transcripts: the extracting model attends worse to material between endpoints, so "the transcript is still there" doesn't mean the extraction sees it equally.
brgsk
·2 bulan yang lalu·discuss
[flagged]
brgsk
·2 bulan yang lalu·discuss
thats beautiful! wow!
brgsk
·2 bulan yang lalu·discuss
not at all, I appreciate your comments!

yeah i agree with you on not using the terminology, although it's intuitive it's also confusing enough. it's tempting to do that, but i share your sentiment
brgsk
·2 bulan yang lalu·discuss
yeah i used cc to help me write the post itself and the comment, my bad
brgsk
·2 bulan yang lalu·discuss
fair — this post mapped the gaps without making the case for whether filling them changes what an agent can do. the interesting ones are procedural and prospective. both deserve their own post.

thanks for the read.
brgsk
·2 bulan yang lalu·discuss
what the hell is going on at google
brgsk
·3 bulan yang lalu·discuss
Install with

  ```
  uv add "memvee[postgres]"
  ```
- Links:

  - GitHub: https://github.com/vstorm-co/memv

  - Docs: https://vstorm-co.github.io/memv

  - PyPI: https://pypi.org/project/memvee/
- Quickstart:

  ```python
  from memv import Memory
  from memv.embeddings import OpenAIEmbedAdapter
  from memv.llm import PydanticAIAdapter

  memory = Memory(
      db_url="postgresql://user:pass@host/db",
      embedding_client=OpenAIEmbedAdapter(),
      llm_client=PydanticAIAdapter("openai:gpt-4o-mini"),
  )
  ```
brgsk
·4 bulan yang lalu·discuss
Big W for anthropic
brgsk
·7 bulan yang lalu·discuss
Sounds captivating, but not sure what it is
brgsk
·11 bulan yang lalu·discuss
I haven't read anything this insightful and interesting in a long time.