#+HashtagPLUS
In

Menu

#Evals

8 posts

Feed·
8 of 8 posts
GitHub - calmrocks/ai-engineer-notebooks: Hands-on, framework-free Colab notebooks for the AI Engineer / Forward Deployed Engineer (FDE) skill set — model APIs, structured output, tool calling, RAG, evals-as-the-spine, agents (loop from scratch, tool design, guardrails, MCP, Skills), fine-tuning vs LoRA, prompt-injection/security, LLMOps, and customer craft. Runs on the free Groq API.
🖼️
111

GitHub - calmrocks/ai-engineer-notebooks: Hands-on, framework-free Colab notebooks for the AI Engineer / Forward Deployed Engineer (FDE) skill set — model APIs, structured output, tool calling, RAG, evals-as-the-spine, agents (loop from scratch, tool design, guardrails, MCP, Skills), fine-tuning vs LoRA, prompt-injection/security, LLMOps, and customer craft. Runs on the free Groq API.

Hacker News·Hacker News·20 days ago
#mQD00stw
#github#rag#evals#photo#englishlanguage

Hands-on, framework-free Colab notebooks for the AI Engineer / Forward Deployed Engineer (FDE) skill set — model APIs, structured output, tool calling, RAG, evals-as-the-spine, agents (loop from sc...

15s
Read More
📰
260

How does programming language affect token efficiency and correctness?

danluu.com·danluu.com·about 1 month ago
#jTjTe048
#llm#benchmarking#evals#article#ama#englishlanguage

This somewhat widely cited post (I keep seeing it cited, anyway) suggests that dynamic languages and/or languages that represent things more concisely are more token efficient. It seems to be cited enough that LLM search results agree.…

15s
Read More
Eval-driven development: Build better AI faster
🖼️
0

Eval-driven development: Build better AI faster

Vercel News·Malte Ubl·4 months ago
#vOsplPll
#vercel#evals#code#feedback#output#quality

Learn how eval-driven development helps you build better AI faster. Discover a new testing paradigm for AI-native development and unlock continuous improvement.

15s
Read More
GitHub - dirac-run/dirac: Coding Agent singularly focused efficiency and context curation. Reduces API costs by 50-80% vs other agent AND improves the code quality at the same time. Uses Hash Anchored edits, massively parallel operations, AST manipulation and many many other optimizations. https://dirac.run/
📰
0

GitHub - dirac-run/dirac: Coding Agent singularly focused efficiency and context curation. Reduces API costs by 50-80% vs other agent AND improves the code quality at the same time. Uses Hash Anchored edits, massively parallel operations, AST manipulation and many many other optimizations. https://dirac.run/

GitHub·dirac-run·5 months ago
#giDioVm8
#repo#handledialogclose#handleclose#showconsentmanagement#start#dirac

Coding Agent singularly focused efficiency and context curation. Reduces API costs by 50-80% vs other agent AND improves the code quality at the same time. Uses Hash Anchored edits, massively paral...

15s
Read More