Depends on the task — sometimes that will work (see claude-prompt-engineer). If not, even if it takes a little work, it's worth it!
PROMPT ENGINEERING
-
Few-Shot Prompts Make Unexpected Comeback in 2026
By
–
Everyone is sleeping on few-shot prompts They're coming back, in a big way
-
Claude 3 Opus excels with high-quality prompt engineering examples
By
–
Claude 3 Opus + 10 examples is ridiculously capable. Just make sure the examples are super high-quality. Garbage in, garbage out.
-
Multi-shot Prompting Set for Major Resurgence
By
–
Multi-shot prompting is going to come back, in a big way
-
Gemini 1.5 Million Token Context Window Capabilities
By
–
If you want a hint about the future of AI, it is worth trying Gemini 1.5 with the 1M token context window, now available to everyone, apparently. Some of my experiments: giving it a video and having it figure out a recipe, execute instructions, watching my screen, summarize work
-
Perplexity adds search results to ground, Claude does not
By
–
Perplexity adds search results to the prompt to ground it in reality. My screenshots are from http://
Claude.ai, which doesn't have search so it's just the model talking. -
Optimizing LLM Systems with DSPy and LangChain
By
–
Optimization of LLM Systems with DSPy and LangChain/LangSmith There are a lot of novel and interesting ideas in DSPy around optimization of LLM systems Super excited to host a webinar with @lateinteraction and @hwchase17 diving into this topic! https://
us06web.zoom.us/webinar/regist
er/WN_n4HUNqhFQFa4ax3kYrZW8g#/registration
… We've -
Few-Shot Learning: Logging, Feedback, and Self-Learning GPTs
By
–
Great example of the importance of few shot examples How do you get these examples? One way is to have a proper logging + feedback collection service set up You can even automate the "feedback" -> "few shot example" loop – see "self learning GPTs" https://
youtube.com/watch?v=OnQQeW
Ewzyw
… -
Claude Opus 10-shot: Expensive and Slow Trade-offs
By
–
Haha thanks! And yeah 10-shot Opus is ridiculous, but expensive and slow
-
Few-Shot Prompting Technique Boosts Claude 3 Haiku Performance
By
–
Highest alpha secret in AI right now: If you provide ~10 examples to Claude 3 Haiku… it’ll often outperform Claude 3 Opus, and far outperform GPT-4 at a fraction of the cost, with blazing fast speeds