News for hackers. Stuff that matters.
Re:Anthropic publishes the 'system prompts' that make Claude... by criddell on Tuesday August 27, 2024 @11:36AM (#41368737)
It probably shouldn't be called prompt engineering, even informally. The work of an engineer shouldn't require hope.
Re:Anthropic publishes the 'system prompts' that make Claude... by sirspacey on Tuesday August 27, 2024 @11:50AM (#41368883)
This is the fundamental change in the concept of programming

From computer’s doing exactly what you state, with all the many challenges that creates

To is probabilistically solving for your intent, with all the many challenges that creates

Fair to say human beings probably need both to effectively communicate

Will be interesting to see if the current GenAI + ML + prompt engineering + code is sufficient

Re:Anthropic publishes the 'system prompts' that make Claude... by mplewis on Tuesday August 27, 2024 @02:13PM (#41370849)
Nah man. This isn’t solving anything. This is praying to a machine god but it’s an autocomplete under the hood.
Re:Anthropic publishes the 'system prompts' that make Claude... by Loughla on Tuesday August 27, 2024 @08:23PM (#41374761)
Honestly, this sort of programming (whether it's in quotes or not) will be unbelievably life changing when it works.

I can absolutely put into words what I want, but I cannot program it because of all the variables. When a computer can build the code for me based on my description... Holy cow.

Re:Anthropic publishes the 'system prompts' that make Claude... by VirusNewbie on Tuesday August 27, 2024 @08:34PM (#41374845)
if this doesn't work well with super high level languages, why would it work really well with LLMs?
Re:Anthropic publishes the 'system prompts' that make Claude... by Loughla on Tuesday August 27, 2024 @09:59PM (#41375257)
I can have a conversation with LLM's. they can walk me through the troubleshooting without prior knowledge of programming languages.

That seems like a massive advantage.

Re:Anthropic publishes the 'system prompts' that make Claude... by fshbbdssbbgdd on Tuesday August 27, 2024 @03:02PM (#41371496)
I don’t think the people who engineered the Golden Gate Bridge, Apollo 7, or the transistor would have succeeded if they didn’t have hope.
Re:Anthropic publishes the 'system prompts' that make Claude... by Terr_ on Tuesday August 27, 2024 @05:56PM (#41373571)
I think OP's point is that "hope" is never a substitute for "a battery of experiments on dependably constant phenomena and supported by strong statistical analysis."
Re:Anthropic publishes the 'system prompts' that make Claude... by llmfan on Tuesday August 27, 2024 @05:01PM (#41372994)
It should be called prompt science.
Re:Anthropic publishes the 'system prompts' that make Claude... by Loughla on Tuesday August 27, 2024 @08:24PM (#41374767)
It's literature.

I never thought my English degree would be so useful.

This is only half in jest by the way.

Re:Anthropic publishes the 'system prompts' that make Claude... by llmfan on Wednesday August 28, 2024 @05:12AM (#41377563)
So many different areas of knowledge can be leveraged, as long as you're able to experiment and learn.
Re:Anthropic publishes the 'system prompts' that make Claude... by fennecfoxy on Friday August 30, 2024 @08:40AM (#41400113)
Engineering requires hope; anything outside the bounds of our understanding (like exactly how these models work) requires it.

Scientists fold proteins, _hoping_ that they'll find the right sequence, based on all they currently know (best guess).

Without hope there is no need try; without trying there is no discovery.

Re:Anthropic publishes the 'system prompts' that make Claude... by valval on Saturday August 31, 2024 @07:00PM (#41412692)
What a silly thing to say. Engineering is just problem solving.