I find the word "engineering" used in this context extremely annoying. There is no "engineering" here. Engineering is about applying knowledge, laws of physics, and rules learned over many years to predictably design and build things. This is throwing stuff at the wall to see if it sticks.
einrealist 1 hours ago [-]
I call it "Vibe Prompting".
Even minor changes to models can render previous prompts useless or invalidate assumptions for new prompts.
whatever1 53 minutes ago [-]
In today’s episode of Alchemy for beginners!
Reminds me of a time that I found I could speed up by 30% an Algo in a benchmark set if I seed the random number generator with the number 7. Not 8. Not 6. 7.
raffael_de 2 hours ago [-]
Should have "(2024)" in the submission title.
babblingfish 7 hours ago [-]
The big unlock for me reading this is to think about the order of the output. As in, ask it to produce evidence and indicators before answering a question. Obviously I knew LLMs are a probabilistic auto complete. For some reason, I didn't think to use this for priming.
stingraycharles 2 hours ago [-]
I typically ask it to start with some short, verbatim quotes of sources it found online (if relevant), as this grounds the context into “real” information, rather than hallucinations. It works fairly well in situations where this is relevant (I recently went through a whole session of setting up Cloudflare Zero Trust for our org, this was very much necessary).
beering 6 hours ago [-]
Note that this is not relevant for reasoning models, since they will think about the problem in whatever order it wants to before outputting the answer. Since it can “refer” back to its thinking when outputting the final answer, the output order is less relevant to the correctness. The relative robustness is likely why openai is trying to force reasoning onto everyone.
adastra22 3 hours ago [-]
This is misleading if not wrong. A thinking model doesn’t fundamentally work any different from a non-thinking model. It is still next token prediction, with the same position independence, and still suffers from the same context poisoning issues. It’s just that the “thinking” step injects this instruction to take a moment and consider the situation before acting, as a core system behavior.
But specialized instructions to weigh alternatives still works better as it ends up thinking about thinking, thinking, then making a choice.
simianwords 2 hours ago [-]
I think you are misleading as well. Thinking models do recursively generate the final “best” prompt to get the most accurate output. Unless you are genuinely giving new useful information in the prompt, it is kind of useless to structure the prompt in one way or another because reasoning models can generate intermediate steps that give best output. The evidence on this is clear - benchmarks reveal that thinking models are way more performant.
adastra22 6 hours ago [-]
Furthermore, the opposite behavior is very, very bad. Ask it to give you an answer and justify it, it will output a randomish reply and then enter bullshit mode rationalizing it.
Ask it to objectively list pros and cons from a neutral/unbiased perspective and then proclaim an answer, and you’ll get something that is actually thought through.
vincnetas 3 hours ago [-]
It's one year old. Curious how much of it is irrelevant already. Would be nice to see it updated.
gdudeman 8 hours ago [-]
This is written for the 3 models (Sonnet, Haiku, Opus 3). While some lessons will be relevant today, others will not be useful or necessary on smarter, RL’d models like Sonnet 4.5.
> Note: This tutorial uses our smallest, fastest, and cheapest model, Claude 3 Haiku. Anthropic has two other models, Claude 3 Sonnet and Claude 3 Opus, which are more intelligent than Haiku, with Opus being the most intelligent.
cjbarber 7 hours ago [-]
Yes, Chapters 3 and 6 are likely less relevant now. Any others? Specifically assuming the audience is someone writing a prompt that’ll be re-used repeatedly or needs to be optimized for accuracy.
111yoav 4 hours ago [-]
Is there an up to date version of this that was written against their latest models?
ipnon 54 minutes ago [-]
I really struggle to feel the AGI when I read such things. I understand this is all of year old. And that we have superhuman results in mathematics, basic science, game playing, and other well-defined fields. But why is it difficult to impossible for LLMs to intuit and deeply comprehend what it is we are trying to coax from them?
xanderlewis 49 seconds ago [-]
> superhuman results in mathematics
LLMs mostly spew nonsense if you ask them basic questions on research or even master's degree-level mathematics. I've only ever seen non-mathematicians suggest otherwise, and even the biggest mathematician advocate for AI, Terry Tao, seems to recognise this too.
Rendered at 10:33:06 GMT+0000 (Coordinated Universal Time) with Vercel.
Even minor changes to models can render previous prompts useless or invalidate assumptions for new prompts.
Reminds me of a time that I found I could speed up by 30% an Algo in a benchmark set if I seed the random number generator with the number 7. Not 8. Not 6. 7.
But specialized instructions to weigh alternatives still works better as it ends up thinking about thinking, thinking, then making a choice.
Ask it to objectively list pros and cons from a neutral/unbiased perspective and then proclaim an answer, and you’ll get something that is actually thought through.
> Note: This tutorial uses our smallest, fastest, and cheapest model, Claude 3 Haiku. Anthropic has two other models, Claude 3 Sonnet and Claude 3 Opus, which are more intelligent than Haiku, with Opus being the most intelligent.
LLMs mostly spew nonsense if you ask them basic questions on research or even master's degree-level mathematics. I've only ever seen non-mathematicians suggest otherwise, and even the biggest mathematician advocate for AI, Terry Tao, seems to recognise this too.