Tell HN: OpenAI silently removed Study Mode from ChatGPT

https://news.ycombinator.com/item?id=47739305

by smokel • 3 months ago

189 78 3 months ago

news.ycombinator.com

Here's hoping that it will return soon, as I really liked it.

brumar• 3 months ago

After all, this "mode" was just a system prompt (last time I looked).

tomrod• 3 months ago

Can it be replicated by a user?

shlewis• 3 months ago

https://raw.githubusercontent.com/0xeb/TheBigPromptLibrary/r...

I think this is pretty much the entirety of study mode. Never used it before but as long as there's no UI changes, yes, it's 100% replicable.

box2• 3 months ago

There used to be a “Custom GPT” feature which basically just creates a prompt wrapper with some extra functionality like being able to call web APIs for more data. Can’t seem to find that menu right now, but it would have easily replicated the study feature. Maybe it was limited to paid accounts only.

toomanyrichies• 3 months ago

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.

beering4• 3 months ago

But also, if you liked the feature, can’t you just ask chatgpt to tutor you? Does it work as well as the pre-baked Study Mode?

raincole• 3 months ago

I think it's just that AI isn't that accurate and they've observed some backfire from teachers/students.

vineyardmike• 3 months ago

Re: product strategy

Honestly, it probably led to long conversations. The tokens/GPU time for one long conversation is more expensive than multiple short conversations. They’re trying to shore up their finances, and they’re moving away from the consumer market and towards enterprise, and students were probably a bad demographic to sell to.

fg137• 3 months ago

So?

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

senectus1• 3 months ago

anyone get a copy of the prompt?

janpmz• 3 months ago

I was concerned about big players offering the same functionality when building listendock.com, but maybe there is a place for specialized apps like that.

el_io• 3 months ago

Haven't use 'Study Mode' in OpenAI, but can't you just ask it to act as a study coach or whatever you want it to be?

altmanaltman2• 3 months ago

I remember videos with titles like "OPENAI CHANGED STUDYING COMPLETELY WITH THIS ONE SUPER UPDATE!" and obnoxious thumbnails on youtube when it was first launched. I guess studying changed it.

danielbln• 3 months ago

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

altmanaltman2• 3 months ago

https://news.ycombinator.com/item?id=44725764

Also discussed on HN. Yeah I can ignore them, but a lot of people watch those videos and fall for the grift (going by their views) and that's sad. It personally annoys me also when yt recommends them to me because it thinks I'm interested in software

ddtaylor• 3 months ago

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

sitkack2• 3 months ago

https://dearrow.ajay.app/

CatDeveloper_• 3 months ago

they do it with other stuff to i feel like they see how much users actually interact with those features and base their decsisoins kinda like how google owuld remove some features at random..

foundermodus• 3 months ago

What was the Study Mode? I never saw it.

exitb• 3 months ago

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

ok123456• 3 months ago

Gemini still has its study mode.

llagerlof• 3 months ago

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

jegudiel• 3 months ago

I used to enjoy studying with ChatGPT too. I was on their Plus plan.

tmpz22• 3 months ago

Do you remember anything you “studied”?

FergusArgyll• 3 months ago

I do, bwrap.

It's not very complicated and I actually wanted to learn it. AI doesn't make learning magically easier, but it writes decent quizzes and debugs answers so it's better than just reading the manual

m-hodges• 3 months ago

I tried it a few times and always found it disappointing. It typically started off like a structured "lesson" but as I chatted with it, it would forget the syllabus is had proposed and we never "completed" the thing we set out to learn.

utopiah• 3 months ago

Before this Sora, and before that large government contracts. I don't think they care so much for the random consumer anymore. They use anything and everyone for PR but they get closer to IPO they are focusing what actually might make them profitable.

TL;DR: bet on stuff being removed

shivang2607• 3 months ago

Do people even used that ?

iugtmkbdfil834• 3 months ago

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 ).

derrida• 3 months ago

Has ChatGPT gotten worse over past few months or is it I just have seen other things higher quality, or they stopped caring about user or something?

All of a sudden feels like it gives me boilerplate and boiler plate of PR and cheesy reasoning, and like no actual answers - worse even - highly confident wrong answers that it then seeks to justify or explain (like it doesn't seem humble enough to be like "Actually, got that wrong" or if challenged it just caves over, accepts too readilythe assumptions in what the user is asking, or just blindly accepts a premise of the question) it's almost useless, like before it used to seem like could get it to emulate the way a certain writer or discourse speaks, now it seems like this derpy highschool just wants to be in kid that went into public relations and the language no matter what the topic seems always the same, it's really spammy feeling,

I could be asking it questions about like how medieval monks talked about light and the breath in latin and it will be replying like I'm interested in monetising or improving my lifestyle or some b.s. I don't think it used to be this way?

reminds of a circa 2003-6 wordpress sites - blackhat seo - feeling to generate back links to push affiliate links or something, with markov generated content designed to push back links for the actual human written landing page

It's not like this on the other llms, something's up.

Or maybe they have just found the niche and it is a bunch of people who do think like that - like I dunno - middle management the world over

that is scary ... bonus ghastly incantations of the epistemology of middle management

omgJustTest2• 3 months ago

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

graerg• 3 months ago

They made a big point of explicitly advertising this as a feature with the GPT-5 rollout, no? Routing to cheaper models/less reasoning depending on the input prompt.

ssk42• 3 months ago

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

suburban_strike• 3 months ago

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

MattRix• 3 months ago

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).

beering4• 3 months ago

Yeah I set thinking as my default and never looked back. It’s my daily driver and extended thinking is usually not too slow. The way that the “instant” model trades quality for speed is not worth it and I don’t need the instant gratification. (But I also don’t do entertainment chatting so ymmv.)

layer82• 3 months ago

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

beering4• 3 months ago

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

enejej2• 3 months ago

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.

antonvs• 3 months ago

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.

coffeefirst• 3 months ago

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.

Marciplan• 3 months ago

in regards of sunsetting, they are better at being Google than Google is at being Google

treetalker• 3 months ago

FWIW, Kagi Assistant still has a Study mode / custom assistant. It works well and I use it a few times per week.

enejej2• 3 months ago

Another piece of evidence that shows OAI has no vision and taste re. Project selection.

Describes this whole LLM hype really. Will be jarring if it ends up being that the value created (in terms of revenues) is mostly around software production.

drivebyhooting• 3 months ago

I’ve tried using it for working through AIME. It was ok, but significantly worse than a human teacher.

It generally knew how to solve the questions, but does not know how to properly scaffold the solution. It mostly just prompts simple calculations, rather than guide to get the insight. What’s worse is that ChatGPT would occasionally disagree with my calculation because it can’t do arithmetic!

trashface• 3 months ago

They do stuff like that. They also killed "Robot" personality last year which was my favorite. The replaced it with "Efficient" or something, but it isn't the same. Robot was terminator-esq, appropriate for the new age we are entering IMO.

Lwerewolf2• 3 months ago

This.

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

These "little" changes are incredibly annoying.

reactordev• 3 months ago

they are trying to burn your tokens on purpose to make you spend more... like introducing limits but making it so API requests continue, at cost...

afpx• 3 months ago

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

Leynos• 3 months ago

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

egorfine• 3 months ago

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.

bko• 3 months ago

I think its prob enough to do a prompt. Isn't that what these things are? Probably had some extra scaffolding before but now engine is good enough where just saying help me study results in the same results.

I personally dont want modes. It should be smart enough to infer my intention and act accordingly

paulcole• 3 months ago

How would they remove it loudly?

jdthedisciple• 3 months ago

By announcing it?

hbcondo714• 3 months ago

The also removed Chat mode (from their Codex VSCode extension):

https://github.com/openai/codex/issues/11007

r4sz• 3 months ago

We silently remove OAI

Jimmy0252• 3 months ago

Sam just loves doing these kinds of things.

danish001112• 3 months ago

The problem with most "AI study modes" is that they optimize for knowledge transfer. The harder problem is knowledge use, being able to actually apply something under pressure. Reading about how to handle a difficult conversation is not the same as practicing it. Knowing the BATNA framework or some other thing you learn from chatgpt doesn't mean you can use it when someone lowballs you and you have 10 seconds to respond.

elevation• 3 months ago

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?

danish001112• 3 months ago

What: Interview, Date, Conflict resolution (more like holding back to respond), setting boundaries, negotiating, or when you feel threatened like when you were a kid if you were bullied…

How: Like any other skill practice if you were in that kind of situation and you were stuck and trying to do sudo runs as if it was real and getting the right muscle memory.

Just working in it

Tell HN: OpenAI silently removed Study Mode from ChatGPT

Related Stories