discussions Search Results · language:Dune language:Python language:JavaScript language:JavaScript language:JavaScript is:public
Filter by
3.7M results
The language qualifier is not supported when searching discussions. Try searching for repositories instead?
:
Hi Keith,
maybe my idea isn t even possible, but can I use WriterAgent to translate my document (headless) into another language?
Sam
:
Beta Release Notice
Welcome to EduPlay Studio 1.0.0 Beta.
This version is an early public testing release designed to gather feedback, identify bugs, and improve the overall user
experience before a ...
:
Proposal: get_paragraph_metadata — expose a paragraph s style model (named style + direct overrides)
I ve already implemented and tested this on a branch (UNO regression tests pass, gate clean). If you ...
:
Judge v2 is currently used for benchmark evaluation.
Areas under consideration:
- Robustness
- Consistency
- Fairness
- Domain-specific criteria
What improvements would you suggest?
:
https://jimmysong.io/blog/ai-gateway-in-depth/
Step1: 基础
- [x] 基础 AI 协议支持 (SSE/HTTP) #657
- [x] Streamable HTTP (doc/pr) #674
- [x] Token 用量获取 #659
Step2: 兼容
- [x] 面向密钥的负载均衡 apache/dubbo-go-pixiu#696 ...
:
Have you evaluated a model using Industrial Agent Benchmark?
Please share:
- Model name
- Benchmark version
- Evaluation set
- Scores
- Observations
Example:
Model: GPT-5
Version: v1.1.0-pre ...
:
💰 Let s Talk Real Numbers: Monthly Affiliate Income Thread
Hey everyone! 👋
I wanted to kick off something I think a lot of us have been curious about but rarely see discussed honestly in the
open: what ...
:
My code is basically the same as the last example in doc/lib-usage.md, but I suspect the data added from glos.addEntry
are saved in RAM not SQLite. How can I enable SQLite mode when use PyGlossary as a ...
:
We are looking for new benchmark tasks.
Suggested format:
Domain: Difficulty: Task Description: Expected Answer: Evaluation Criteria:
Examples:
- Quality Engineering
- Maintenance
- Production ...