Hacker News

Your comment made me ask myself: "Then why remove it? If it really is just a system prompt, I can't imagine tech debt or maintenance are among the reasons."

My best guess is this is product strategy. A markdown file doesn't require maintenance, but a feature's surface area does. Every exposed mode is another thing to document, support, A/B test, and explain to new users who stumble across it. I'm guessing that someone decided "Study Mode isn't hitting retention metrics", and decided to kill it. As an autodidact, I loved the feature, but as a software engineer I can respect the decision.

What I'm wondering about is whether there's a security angle to this as well. Assuming exposed system prompts are a jailbreak surface, if users can infer the prompt structure, would it make certain prompt injection attacks easier? I'm not well-versed in ML security, and I'd be curious to hear from someone who is.

Can it be replicated by a user?

anyone get a copy of the prompt?

So?

To users, that's a distinct, useful feature, and they don't care about how it's implemented.

This.

They recently made "efficient" even more verbose, my custom instructions can't suppress it properly anymore.

These "little" changes are incredibly annoying.

Yeah, I miss "Robot". It helps to add something along the lines of "Tell it like it is; don't sugar-coat responses. Get right to the point. Be concise." to custom instructions.

Anytime I use a system prompt that attempts to make the LLM “robotic”, I get denied. I have tried on Grok, ChatGPT, Gemini, and Claude. When I ask the LLM why, it says it’s because such system prompts are used to bypass guardrails. Maybe that’s why? idk

They got rid of "nerdy" last month too. Shame

Two questions: under what conditions would you only have 10 seconds to respond? And how would you develop yourself to be effective under this kind of pressure?

[dead]

That's how ChatGPT always seemed to me. One of the reasons I exclusively use other models is it would rather make something up than say "I can't find anything about that."

But I'm starting to wonder about something.

I've noticed a lot of people claiming the models—all the models from all the big providers—are deteriorating, and then go on to describe the problems that skeptics picked up on during their first few days of usage.

The models really could be getting worse. I haven't noticed anything but I don't know.

But do you think its possible that this is more akin to a honeymoon period? Depending on how you use the system and a fair bit of luck, the problems may show up for you pretty early, or may take a while to become obvious.

It's gotten bad enough that I finally cancelled this month in protest. It's not just you.

people have been talking about "models of models" for arbitration opportunity in inference for about 1.5 yrs.

Arbitration idea: if a user doesn't need high QOS of newest LLM, slip them a cheaper LLM, run their query at reduced quality. measure if they cost you fewer $s in the lower QOS. => profit.

For chatgpt the arbitration opportunity looks more like "we could allocate this amount of gpu to training or inference, we are losing money if we offer the highest quality infra"

In addition there's other interesting economics scaling that can be done outside of "models of models" that are far more profitable. I won't go over all of them (and some of them I feel are quite powerful) but the laziest one is that subscription models count on some zombie users as a counterweight to highly expensive single users, and as a source of stable cashflow.

Zombie users are ones that are paying for sub but not actively or barely using the service

All models are variable in quality simply because they need to do some financial engineering to make the financial standing somewhat healthier. There’s a lot of fear in the market and need for signalling around the viability of the business of llm models and generating returns on invested capital.

Set your default mode to thinking and set some custom instructions. Night and day difference in UX.

If I recall correctly, in their pivot to Codex they took a sizable amount of compute away from ChatGPT

Are you using the free or the paid version? Did you try personalization settings other than the default?

I think you have it set to the wrong mode. If you set it to Thinking with “Extended” thinking effort, is it slower but almost never wrong (because it searches the web to get verify all its assumptions and answers).

Are you using the free service or paid? Because when the free service drops back to older or smaller models, there are noticeable quality differences.

> ghastly incantations of the epistemology of middle management

I mean, LLM writing has been like that from the early on. Its most perfect niche for writing is the LinkedIn blog post.

Teaching the user how to solve problems instead of solving them outright.

Yeah, I had been using ChatGPT's, but Gemini's Pro study mode is excellent as well.

Use DeArrow, it allows you to avoid most of that clickbait farming.

You have these grifter videos for everything, from OpenAI features to hot takes on the strait of Hormuz. These are best ignored entirely.

Do you remember anything you “studied”?

By announcing it?

Anecdotally, I did not even know it was a thing. I either went to tutor me explicitly or purposefully explored a given branch with custom prompts ( + book recommendations on the subject ).