alt Hacker NewsDeepSeek-R1
Comments
I see a lot of people wowing at the test results but have not used it
I am using from past 18 hours and i just great like very good for language model and also it when it's thinking is like awesome
I tried one of their "distill" versions on HF Spaces: https://huggingface.co/spaces/Aratako/DeepSeek-R1-Distill-Qw.... It seems to suffer from the same old repetition and overthinking problems. Using the classic strawberry sniff test:
... Wait, did I count correctly? Let me recount. The word is S-T-R-A-W-B-E-R-R-Y. So positions 3, 8, and 9 are 'R's. That makes three 'R's in total. But I'm a bit confused because when I first wrote it out, I thought maybe only two. Let me double-check. Maybe I miscounted the letters.
Alternatively, perhaps the word doesn't have three 'R's. Let me write it again: S-T-R-A-W-B-E-R-R-Y. So, after E, there are two R's before Y. So that would be two R's, right? Wait, no, in the breakdown, position 3 is R, then position 8 and 9 are R's. So that's three R's. But I'm not sure if that's correct because sometimes people might miscount. ...
Looks promising. Let's hope that the benchmarks and experiments for DeepSeek are truly done independently and not tainted or paid for by them (Unlike OpenAI with FrontierMath.)
It's interesting that, at least through ollama, it appears impossible to get DeepSeek-R1 to give concise answers to questions that don't require any reasoning.
I was wondering if this was related to the (failing?) Rabbit R1 product. Doesn't seem to be--a possible (un)fortunate co-incidence.
My 8-year-old grandson: >What did the scared guy say to the bagel? >I guess I'll have some scream cheese.
Is there any website that shows a performance comparison between different Mac configurations and models?
deepseek v3 and r1 are both 700B models, who has that much memory to run the model locally these days?
benchmark performance seems to hold up on the aider benchmark. R1 comes in on the second place with 56.9% behind O1's 61.7%.
That is just amazing. open source
This is impressive, how do people handle the limited context window of 64k tokens?
I've been using my "5 philosophers sit in a round table. They want to eat." prompt. The answer is hilarious:
``` <think> Okay, so there's this problem with five philosophers sitting around a round table, and they want to eat. Hmm, I'm trying to figure out what exactly is going on here. Is it related to logic puzzles or maybe something about sharing food? The question just says "5 philosophers sit in a round table. They want to eat." It's pretty brief, so I might be missing some context.
Wait, maybe this is similar to the classic puzzle where one person can't eat because everyone else refuses to share their plate unless that person agrees first. But with five people instead of four. Let me think through it step by step.
So, if they're sitting around a table and each has a plate in front of them, right? The goal is for all of them to eat, but there's some sort of rule preventing them from sharing plates. Maybe the idea is that each person can only pass their plate under certain conditions, like only to someone who has more food on their plate than they do.
If I recall correctly, in the four-person puzzle, the first philosopher says, "I'll eat when you eat," and this sort of chain continues until the last person, who then eats because everyone else is waiting. Maybe with five people, a similar logic applies but there's an extra step.
Let me try to outline the scenario:
1. Person A says they won't eat until someone else eats first. 2. Then B says they won't eat unless A eats. 3. C says they won't eat until either A or B eats. 4. D says they won't eat unless someone else has eaten. 5. E, maybe the last one, might have a condition.
Wait, but in this case, each person's condition depends on someone else eating before them, which could create a paradox. If everyone wants someone else to eat first, how does anyone start?
But in the four-person puzzle, it works out because the first person can decide to eat alone, prompting the next to do so, and so on until the last person, who then eats because they're the only one left. So maybe with five people, a similar approach applies but there are more layers.
Let me consider each person's position:
- Let's number them 1 through 5 clockwise around the table. - Suppose person 1 is at the top of the list.
If person 1 decides to eat, they might say, "I'll eat," which allows person 2 to then decide to eat because person 1 has already eaten. Then person 3 can eat after seeing that someone (person 1 or 2) has eaten, and so on.
But wait, in the original puzzle, each person's condition is based on someone else having more than they do, which might complicate things. Maybe it's about passing plates instead of just eating. Let me try to visualize this.
Imagine each person has a plate with some food. The rule is that you can only pass your plate to someone who has less food than you. So if you have more food on your plate, you can pass it along, but only to someone who doesn't have as much.
In the four-person scenario, the first person might pass their plate when they see someone else is willing to accept it. But with five people, this could get tricky because each person's decision affects others.
Alternatively, maybe the problem is about each person refusing to share unless another has eaten, leading to a deadlock where no one can eat until someone breaks the cycle.
Wait, perhaps I'm overcomplicating it. The key might be that in such setups, with an odd number of people, there's always someone who can start the chain by eating alone, breaking the deadlock.
So if person 1 decides to eat despite others not having eaten, that action could prompt person 2 to then eat because person 1 has already started. Then person 3, seeing that at least one person has eaten, would also eat, and so on until all five have eaten.
But in the original puzzle, each person's condition is more specific, like only passing if someone else hasn't eaten yet, which creates a paradox. So maybe here, it's similar but with an extra layer because there's an odd number of people.
I think I'm circling around the idea that with five people, one person can eat first, then the next, and so on until everyone has eaten, using some form of conditional eating based on others' actions.
Perhaps the key is in the order of passing or deciding to eat. Each person's decision depends on someone else having already made a move, which might be possible with an odd number, whereas even numbers can get stuck because every condition requires another to act first, creating an infinite loop.
So, putting it all together, maybe each philosopher in turn eats once they see someone else has started, leading to a chain reaction where eventually, all five can eat. </think>
The problem involves five philosophers sitting around a round table who want to eat but are prevented from sharing plates under certain conditions. The key steps to solve this puzzle are as follows:
1. *Understanding the Conditions*: Each philosopher will only pass their plate (and thus allow themselves to eat) if someone else has already eaten. This creates a chain of dependencies where each person's action depends on another.
2. *Breaking the Deadlock*: In such setups, especially with an odd number of people like five, one person can initiate the process by eating first. This breaks the deadlock because once someone eats, it triggers the next person to do the same, creating a chain reaction.
3. *Chain Reaction*: Starting with one philosopher who decides to eat despite others' conditions, this action prompts the next philosopher in sequence to eat, and so on around the table. Each subsequent person sees that at least one has eaten, allowing them to proceed.
4. *Conclusion*: Eventually, all five philosophers can eat by following this chain of conditional actions, starting with one individual's decision to eat alone.
*Final Answer*: All five philosophers can eat if each starts eating once they see someone else has already done so, beginning a chain reaction around the table. Thus, every philosopher ends up eating. ```
from their Table-3 "the aha moment", can someone explain why the re-evaluation step worth to "aha"? It looks simply repeating the initial step in the exact same way?
Anyone know why Distilled Qwen 1.5b outperforms 4o and sonnet?
Open source models will win the race at the end.
IMHO R1 hallucinates above average
so the real 'Open AI' is in China?
very cool
I wrote an article about the reasoning abilities of LLMs some time ago. During it's creation I discovered that ChatGPT failed this simple /test/ https://www.arnaldur.be/writing/about/large-language-model-r...
One of the DeepSeek-R1 models solve it, but it's a pretty funny solution:
``` User: A man and a goat are on one side of a river. They want to cross it. They have a boat. What steps do they need to follow?
DeepSeek-R1-Distill-Qwen-32B: <think> Okay, so there's this puzzle where a man and a goat are on one side of a river, and they want to cross it using a boat. Hmm, let's see. I remember hearing similar problems before, usually involving other animals or objects, like a wolf and a cabbage, or something like that. Those often require some strategic thinking about what can be left alone and what needs to be taken first.
In this case, though, it's just a man and a goat. That seems simpler, but maybe there's a catch I'm not seeing. Let me think step by step. So, the man needs to get the goat across the river. The boat is there, so they can use that. But is there anything else involved? I mean, sometimes in these puzzles, you have other elements that complicate things, like a wolf or something else that can't be left alone with the goat. But here, it's only the man and the goat.
Wait, perhaps the simplicity is the key. Maybe the answer is straightforward because there's only two things involved—the man and the goat. So, the steps would be something like: the man takes the goat into the boat, rows across, and then they're both on the other side. That seems too easy, but maybe that's it. I mean, when you have more items, you have to be careful about leaving certain things alone, but here, since it's just the man and the goat, there's no risk of anything getting into trouble if left alone.
But maybe I'm missing something. Let me visualize it. The man is on one side, the goat is with him. He gets into the boat, takes the goat with him, rows across the river, and then they're both on the other side. There's no mention of anything else he needs to bring back or anything else on the other side. So, maybe the solution is just that simple.
Alternatively, sometimes in these puzzles, the boat can only carry one or two, but in this case, since it's the man and the goat, maybe the boat can hold both. I think the key here is that there are no other animals or items to worry about, so the steps are straightforward.
Wait, but in the traditional puzzle, the man has to take items across, and sometimes has to make multiple trips because he can't leave certain things unattended. But since here it's only the man and the goat, maybe the problem is designed to test if the person recognizes that the only complication (like in the classic puzzle with another animal) isn't present here, so the steps are much simpler.
So, to break it down:
Man and goat are on the starting side.
Man gets into the boat with the goat.
Man rows the boat to the other side.
They both arrive safely on the other side.
Yeah, I think that's it. No need to worry about leaving the goat alone because there's nothing else to cause a problem. So, the answer is simple in this case. </think>
The man and the goat can cross the river in one smooth trip since there are no other elements to complicate the process. Here's how they do it:
Board the Boat: The man gets into the boat with the goat.
Row Across the River: The man rows the boat to the opposite side.
Arrive Safely: Both the man and the goat safely reach the other side.
I'm curious to know if there is a good reason for this very rambly style of speech.
test
For anyone wanting GGUFs, I uploaded them to https://huggingface.co/collections/unsloth/deepseek-r1-all-v...
There's the distilled R1 GGUFs for Llama 8B, Qwen 1.5B, 7B, 14B, and I'm still uploading Llama 70B and Qwen 32B.
Also I uploaded a 2bit quant for the large MoE (200GB in disk size) to https://huggingface.co/unsloth/DeepSeek-R1-GGUF
It's looking like China beat the US in AI at this juncture, given the much reduced cost of this model, and the fact that they're giving it away, or at least fully open sourcing it.
They're being an actual "Open AI" company, unlike Altman's OpenAI.
[dead]
[dead]
[dead]
[dead]
China is working from a place of deeper Wisdom (7D Chess) than the US
US: NO MORE GPUs FOR YOU
CHINA: HERE IS AN O1-LIKE MODEL THAT COST US $5M NOT $500M
... AND YOU CAN HAVE IT FOR FREE!
[dead]
[dead]
Every reasoning inquiry should start with this Reasoning 101 question. R1 got it right -
https://chatlabsai.com/open-chat?shareid=MbSUx-vUDo
How many words are there in your response to this prompt?
There are 7 words in this response.
Promising start.
For comparison here is the 4o response - https://chatlabsai.com/open-chat?shareid=PPH0gHdCjo
There are 56 words in my response to this prompt.
Deepseek is well known to have ripped off OpenAI APIs extensively in post training, embarrassingly so that it sometimes calls itself “As a model made by OpenAI”.
At least don’t use the hosted version unless you want your data to go to China
I'm curious about whether anyone is running this locally using ollama?