tacoooooooo
- Karma
- 0
- Created
- ()
- Submissions
- 0
- Small LLMs vs. Fine-Tuned Bert for Classification: 32 Experiments (alex-jacobs.com)
-
Hey HN, I built TinyFn because LLMs are bad at the boring stuff — counting letters, validating emails, converting units. But they're even worse at things that are literally impossible for them: hashing, regex execution,…
- Show HN: TinyFn – Your agent sucks at math (tinyfn.io)
I built TinyFn because I kept watching AI agents confidently get basic things wrong — math, string counting, unit conversions, validations. The classic "how many R's in strawberry" problem, but across hundreds of…
- Traditional NLP is not dead (alex-jacobs.com)
- Show HN: The Lobste.rs invitation tree, visualized (alexjacobs08.github.io)
Lobste.rs makes its entire invitation tree public. I scraped it and built this interactive visualization. Some interesting patterns: - The top 10 inviters are responsible for ~40% of all users. - The tree is…
- Show HN: Generate a 1M-document RAG eval dataset from a single prompt (alexjacobs08.github.io)
- Show HN: Dataset Factory – Generate RAG evaluation datasets from a text prompt (alexjacobs08.github.io)
- Generate RAG evaluation datasets from a single prompt (1K to docs) (alexjacobs08.github.io)
- The Case Against PGVector (alex-jacobs.com)
- LLM Features That Ship: Extraction, Generation, and Classification (alex-jacobs.com)
- A Computer Made This (alex-jacobs.com)
- Mastering Integration Testing with FastAPI (alex-jacobs.com)
- Mastering Integration Testing with FastAPI (alex-jacobs.com)
- Effective Error Handling (alex-jacobs.com)