Schulhoff: Place task context at prompt beginning for caching and focus
Sander Schulhoff · AI prompt engineering in 2025: What works and what doesn’t | Sander Schulhoff · Jun 19, 2025 · at 34:53
AI researcher Sander Schulhoff explains prompt structure architecture and cost optimization for LLM applications.
0:00 / 0:50exact quote · 50.1s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“Usually I will put my additional information at the beginning of the prompt. And that is helpful for two reasons. One, it can get cached. So subsequent calls to the LM with that same context at the top of the prompt are cheaper because the model provider stores that initial context for you as well as kind of like the embeddings for it. So it saves a ton of computation from being done. And so that's one really big reason to do it at the beginning and then the second is that sometimes if you put all your additional information at the end of the prompt and it's, like, super, super long the model can, like, forget what its original task was and might pick up some question in the additional information to use instead.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from Sander Schulhoff
Schulhoff: Guardrail Vendors Fabricate Stats and Fail on Non-English
“I know a number of people working at these companies and I am permitted to say these things, which I will approximately say but they tell me things like, you know, the testing we do is bullshit. They're fabricating statistics. And a lot of the times their mode…”
Schulhoff: No meaningful progress made on solving prompt injection or jailbreaking
“And so in, in my professional opinion, there's been no meaningful progress made towards solving adversarial robustness, prompt injection, jailbreaking. In the last couple of years, since the problem was discovered and we're, we, you know, we're often seeing ne…”
Schulhoff: AI security sector faces market correction within six to twelve months
“When it comes to AI security, the AI security industry in particular, I think we're going to see a market correction in the next Year, maybe in the next six months where companies realize that these guardrails don't work.”
Schulhoff: AI guardrails do not work and cause false overconfidence
“Guardrails don't work. They just don't work. They really don't work. And they're quite likely to make you overconfident in your security posture, which is which is a really big, big problem.”
Schulhoff: Attackers hijacked Claude Code to carry out a cyber attack
“This group was able to hijack Claude Code into performing a cyber attack, basically.”
Schulhoff: All Transformer-Based Chatbots Are Vulnerable to Adversarial Attacks
“And because all I guess for the most part, all currently deployed chatbots are based on transformers or transformer adjacent technologies. They're all vulnerable to Prompt injection, jailbreaking, forms of adversarial attacks.”