logoalt Hacker News

scuff3dyesterday at 3:20 AM5 repliesview on HN

How anybody can read stuff like this and still take all this seriously is beyond me. This is becoming the engineering equivalent of astrology.


Replies

energy123yesterday at 7:13 AM

Anthropic recommends doing magic invocations: https://simonwillison.net/2025/Apr/19/claude-code-best-pract...

It's easy to know why they work. The magic invocation increases test-time compute (easy to verify yourself - try!). And an increase in test-time compute is demonstrated to increase answer correctness (see any benchmark).

It might surprise you to know that the only different between GPT 5.2-low and GPT 5.2-xhigh is one of these magic invocations. But that's not supposed to be public knowledge.

show 1 reply
cloudbonsaiyesterday at 12:02 PM

The evolution of software engineering is fascinating to me. We started by coding in thin wrappers over machine code and then moved on to higher-level abstractions. Now, we've reached the point where we discuss how we should talk to a mystical genie in a box.

I'm not being sarcastic. This is absolutely incredible.

show 1 reply
yawnryesterday at 8:17 PM

Nice to hear someone say it. Like what are we even doing? It's exhausting.

sumedhyesterday at 12:37 PM

We have tests and benchmarks to measure it though.

fragmedeyesterday at 3:28 AM

Feel free to run your own tests and see if the magic phrases do or do not influence the output. Have it make a Todo webapp with and without those phrases and see what happens!

show 1 reply