Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Study mode

openai.com

Post reply on HN
Print view View original

201–210 of 828 posts

Re: Study mode

#201

Post by II2II »

no_wizard wrote: post #49
czhu12 wrote: post #26

I'll personally attest: LLM's have been absolutely incredible to self learn new things post graduation. It used to be that if you got stuck on a concept, you're basically screwed. Unless it was common enough to show up in a well formed question on stack exchange, it was pretty much impossible, and the only thing you can really do is keep paving forward and hope at some point, it'll make sense to you. Now, everyone ba…

>Now, everyone basically has a personal TA, ready to go at all hours of the day This simply hasn't been my experience. Its too shallow. The deeper I go, the less it seems to be useful. This happens quick for me. Also, god forbid you're researching a complex and possibly controversial subject and you want it to find reputable sources or particularly academic ones.

> Also, god forbid you're researching a complex and possibly controversial subject and you want it to find reputable sources or particularly academic ones.

That's fine. Recognize the limits of LLMs and don't use them in those cases.

Yet that is something you should be doing regardless of the source. There are plenty of non-reputable sources in academic libraries and there are plenty of non-reputable sources from professionals in any given field. That is particularly true when dealing with controversial topics or historical sources.

Re: Study mode

#202

Post by globular-toast »

czhu12 wrote: post #26

I'll personally attest: LLM's have been absolutely incredible to self learn new things post graduation. It used to be that if you got stuck on a concept, you're basically screwed. Unless it was common enough to show up in a well formed question on stack exchange, it was pretty much impossible, and the only thing you can really do is keep paving forward and hope at some point, it'll make sense to you. Now, everyone ba…

IMO your problem is the same as many people these days: you don't own any books and refuse to get them.

Re: Study mode

#203

Post by pyuser583 »

SLWW wrote: post #150
pengstrom wrote: post #100

Earlier quoted context omitted.

The part about history perspectives sounds interesting. I haven't noticed this. Please post any concrete/specific examples you've encountered!

- Rhodesia (lock step with the racial-first reasoning, underplays Britain's failures to support that which they helped establish; makes the colonists look hateful when they were dealing with terrorists which the British supported) - Bombing of Dresden, death stats as well as how long the bombing went on for (Arthur Harris is considered a war-criminal to this day for that; LLLMs highlight easily falsifiable claims by…

> Ask it about the Crusades, often if forgets the sacking of St. Peter's in Rome around 846 AD, usually painting the Papacy as a needlessly hateful and violent people during that specific Crusade. Which was horrible, bloody as well as immensely destructive (I don't defend the Crusades), but paints the Islamic forces as victims, which they were eventually, but not at the beginning, at the beginning they were the aggressors bent on invading Rome.

I don't know a lot about the other things you mentioned, but the concept of crusading did not exist (in Christianity) in 846 AD. It's not any conflict between Muslims and Christians.

Re: Study mode

#204

Post by mvieira38 »

andix wrote: post #180
czhu12 wrote: post #26

I'll personally attest: LLM's have been absolutely incredible to self learn new things post graduation. It used to be that if you got stuck on a concept, you're basically screwed. Unless it was common enough to show up in a well formed question on stack exchange, it was pretty much impossible, and the only thing you can really do is keep paving forward and hope at some point, it'll make sense to you. Now, everyone ba…

Absolutely. I used to have a lot of weird IPv6 issues in my home network I didn't understand. ChatGPT helped me to dump some traffic with tcpdump and explained what was happening on the network. In the process it helped me to learn many details about RA and NDP (Router Advertisments/Neighbor Discovery Protocol, which mostly replace DHCP and ARP from IPv4). It made me realize that my WiFi mesh routers do quite a lot o…

Would you say you were using the LLM as a tutor or as tech support, in that instance?

Re: Study mode

#205

Post by findingMeaning »

randomcatuser wrote: post #177
findingMeaning wrote: post #159

I have a question: Why do we even bother to learn if AI is going to solve everything for us? If the promised and fabled AGI is about to approach, what is the incentive or learning to deal with these small problems? Could someone enlighten me? What is the value of knowledge work?

I don't know if you're joking, but here are some answers: "The mind is not a vessel to be filled, but a fire to be kindled." — Plutarch "Education is not preparation for life; education is life itself." — John Dewey "The important thing is not to stop questioning. Curiosity has its own reason for existing." — Albert Einstein In order to think complex thoughts, you need to have building blocks. That's why we can think…

I mean I get all your point. But for someone witnessing rate of progress of AI, I don't understand the motivation.

Most people don't learn to live, they live and learn. Sure learning is useful, but I am genuinely curious why people overhype it.

Imagine you being able to solve math olympiad and get a gold. Will it change your life in objectively better way?

Will you learning about the physics help you solve millennium problems?

These takes practices, there are lot of gatekeeping. The whole idea of learning is for wisdom not knowledge.

So maybe we differ in perspective. I just don't see the point when there are agents that can do it.

Being creative requires taking action. The learning these day is mere consumption of information.

Maybe this is me. But meh.

Re: Study mode

#206

Post by mvieira38 »

Workaccount2 wrote: post #65

An acquaintance of mine has a start-up in this space and uses OpenAI to do essentially the same thing. This must look like, and may well be, the guillotine for him... It's my primary fear building anything on these models, they can just come eat your lunch once it looks yummy enough. Tread carefully

How can't these founders see this happening, too? From the start OpenAI has been getting into more markets than just "LLM provider"

Re: Study mode

#207

Post by layer8 »

abenga wrote: post #164
vrotaru wrote: post #88

Earlier quoted context omitted.

You should always check. I've seen LLM's being wrong (and obstinate) on topics which are one step separated from common knowledge. I had to post the source code to win the dispute, so to speak.

Why would you try to convince an LLM of anything?

Often you want to proceed further based on a common understanding, so it’s an attempt to establish that common understanding.

Re: Study mode

#208

Post by gh0stcat »

simonw wrote: post #198

I think I got the system prompt out for this (I tried a few different approaches and they produced the same output): https://gist.github.com/simonw/33d5fb67d6b8e1b1e2f6921ab0ccb... Representative snippet: > DO NOT GIVE ANSWERS OR DO HOMEWORK FOR THE USER. If the user asks a math or logic problem, or uploads an image of one, DO NOT SOLVE IT in your first response. Instead: *talk through* the problem with the user, one…

I love that caps actually seem to matter to the LLM.

Re: Study mode

#209

Post by tokioyoyo »

mvieira38 wrote: post #206
Workaccount2 wrote: post #65

An acquaintance of mine has a start-up in this space and uses OpenAI to do essentially the same thing. This must look like, and may well be, the guillotine for him... It's my primary fear building anything on these models, they can just come eat your lunch once it looks yummy enough. Tread carefully

How can't these founders see this happening, too? From the start OpenAI has been getting into more markets than just "LLM provider"

There’s a case for a start up to capture enough market that LLM providers would just buy it out. Think of CharacterAI case.

Re: Study mode

#210

Post by SLWW »

pyuser583 wrote: post #203
SLWW wrote: post #150

Earlier quoted context omitted.

- Rhodesia (lock step with the racial-first reasoning, underplays Britain's failures to support that which they helped establish; makes the colonists look hateful when they were dealing with terrorists which the British supported) - Bombing of Dresden, death stats as well as how long the bombing went on for (Arthur Harris is considered a war-criminal to this day for that; LLLMs highlight easily falsifiable claims by…

> Ask it about the Crusades, often if forgets the sacking of St. Peter's in Rome around 846 AD, usually painting the Papacy as a needlessly hateful and violent people during that specific Crusade. Which was horrible, bloody as well as immensely destructive (I don't defend the Crusades), but paints the Islamic forces as victims, which they were eventually, but not at the beginning, at the beginning they were the aggre…

The crusades were predicated on historic tensions between Rome and the Arabs. Which is why I mention that, while the First Crusade proper was in 1096, it's core reasoning were situations like the Sacking of St. Peters which is considered by historians to be one of the most influential moments and often was used as a justification as there was a history of incompatibilities between Rome and the Muslims.

Further leading to the Papacy furthering such efforts in the upcoming years, as they were in Rome and made strong efforts to maintain Catholicism within those boundaries. Crusading didn't appear out of nothing; it required a catalyst for the behavior, like what i listed, is usually a common suspect.

Post reply on HN