svcrunch

The grandparent is definitely wrong on (3). Yes, coding is a killer product, I agree with you.

On (2), I agree with you for local models. BUT, there are also the open source Chinese models accessible via open-router. Your argument ("don't hold a candle to SOTA models") does not hold if the comparison is between those.

On (1), I agree more with the grandparent than with your assessment. Yes, OpenAI and Anthropic are killing it for now, but the time horizon is very short. I use codex and claude daily, but it's also clear to me that open source is catching up quickly, both w.r.t. the models and the agentic harnesses.

svcrunch

4 ay öncediscuss

I generally don't waste time with patents. I think most patents in deep learning can be overturned by prior art.

My current approach to IP is trade secrets. If we publish, we are careful to avoid details that would make the techniques easy to productionize.

svcrunch

5 ay öncediscuss

Thanks for your interest. The rerankers are external, GoodMem is a unified API layer that calls out to various providers. There's no model running inside the database or the GoodMem server.

We support both commercial APIs and self-hosted options:

  - Cohere (rerank-english-v3.0, etc.)
  - Voyage AI (rerank-2.5)
  - Jina AI (jina-reranker-v3)

Self-hosted (no API key needed):

  - TEI - https://github.com/huggingface/text-embeddings-inference
  - vLLM - https://docs.vllm.ai/en/v0.8.1/serving/openai_compatible_server.html#rerank-api

You register a reranker once with the CLI:

  # Cohere
  goodmem reranker create \
    --display-name "Cohere" \
    --provider-type COHERE \
    --endpoint-url "https://api.cohere.com" \
    --model-identifier "rerank-english-v3.0" \
    --cred-api-key "YOUR_API_KEY"

  # Self-hosted TEI (e.g., BAAI/bge-reranker-v2-m3)
  goodmem reranker create \
    --display-name "TEI Local" \
    --provider-type TEI \
    --endpoint-url "http://localhost:8081" \
    --model-identifier "BAAI/bge-reranker-v2-m3"

Then you can experiment interactively through the TUI.

  goodmem memory retrieve \
    --space-id <your-space> \
    --post-processor-interactive \
    "your query"

For your setup, I think TEI is probably the path of least resistance, it has first-class reranker support and runs well on CPU.

svcrunch

5 ay öncediscuss

Hi there, thanks for writing and sharing your experiences. I'm one of the builders of GoodMem (https://goodmem.ai/), which is infra to simplify end-to-end RAG/agentic memory systems like the one you built.

It's built on Postgres, which I know you said you left behind, but one of the cool features it supports is hybrid search over multiple vector representations of a passage, so you can do a dense (e.g. nomic) and sparse (e.g. splade) search. Reranking is also built in, although it lacks automatic caching (since, in general, the corpus changes over time)

It also deploys to fly.io/railway and costs a few bucks a month to run if you're willing to use cloud-hosted embedding models (otherwise, you can run TEI/vLLM on CPU or GPU for the setup you described).

I hope it's helpful to someone.

svcrunch

geçen yıldiscuss

Here's a problem that no frontier model does well on (f1 < 0.2), but which I think is relatively easy for most humans:

https://dorrit.pairsys.ai/

> This benchmark evaluates the ability of multimodal language models to interpret handwritten editorial corrections in printed text. Using annotated scans from Charles Dickens' "Little Dorrit," we challenge models to accurately capture human editing intentions.

svcrunch

geçen yıldiscuss

This is really cool.

svcrunch

geçen yıldiscuss

Various frontier LLMs were evaluated on their ability to interpret handwritten proofreading marks in printed literary text, using a small benchmark based on Charles Dickens's "Little Dorrit". Results are modest at best, and surprisingly variable across repeated runs, even on the same pages, underscoring the challenge in building reliable, structured-document systems with current multimodal LLMs.

Curious to hear thoughts from others working on similar problems.

Submissions

GPT-5.4 Scores 0.62 F1 on Understanding Handwritten Edits in Dickens

Can GPT-4o Accurately Read Handwritten Proofreading Marks?

comments