311–320 of 339 posts
Earlier quoted context omitted.
If you mean through the user friendly chat GPT website, they're probably making it output as few tokens as possible to cut costs
Wow, imagine paying so they can experiment on you and limit what you get. I so wish i found such … useful clients for my own projects.
Earlier quoted context omitted.
> GPT 4 can continue a completion contrary to your belief When did I say that? I said they work differently. Claude has nothing in between the prefill and the result, OpenAI has tokens between the last assistant message and the result, this makes it different. You cannot prefill in OpenAI, Claude's prefill is powerful as it effectively allows you to use it as general completion model, not a chat model. OpenAI does no…
a) gpt-3.5-turbo has a completion endpoint version as of June: `gpt-3.5-turbo-instruct` b) Even the chat tuned version does completions, if you go via Azure and use ChatML you can confirm it for yourself. They trained the later checkpoints to do a better job at restarting from scratch if the output doesn't match it's typical output format to avoid red teaming techniques. What you keep going on about is the token... w…
We were not talking about that model and I'm 99.999% sure you do not use that model. You might as well mention text-davinci-003 and all the legacy models, you're muddying the waters.
> b) Even the chat tuned version does completions, if you go via Azure and use ChatML you can confirm it for yourself. They trained the later checkpoints to do a better job at restarting from scratch if the output doesn't match it's typical output format to avoid red teaming techniques.
Don't fucking say "even", I know you know I know it can technically do completions as it is just GPT, the issue is what they do with the prompt in the backend.
I do not have Azure to test it, that is interesting but how come you're only mentioning it now? That's more interesting. Anyway, are you sure you can actually prefill with it? You saying that it restarts from scratch tells me it either isn't actually prefilling (and doing a completion) or that there are filters on top which makes it a moot point.
The documentation doesn't mention prefilling or similar but it does say this: This provides lower level access than the dedicated Chat Completion API, but also [...] only supports gpt-35-turbo models [...]
Shame.
> What you keep going on about is the token... which is functionally identical to the `Human:` message for Anthropic.
Now you got it? Jesus Christ, but also no, I mean "\n\nAssistant:" which is not added on in Anthropic's backend like OpenAI does, you have to do it yourself as stated in the Anthropic docs which means you can use it as a completion model as stated in the Anthropic docs, which makes it trivial to bypass any and all refusals.
Not infuriating at all.
Earlier quoted context omitted.
a) gpt-3.5-turbo has a completion endpoint version as of June: `gpt-3.5-turbo-instruct` b) Even the chat tuned version does completions, if you go via Azure and use ChatML you can confirm it for yourself. They trained the later checkpoints to do a better job at restarting from scratch if the output doesn't match it's typical output format to avoid red teaming techniques. What you keep going on about is the token... w…
> a) gpt-3.5-turbo has a completion endpoint version as of June: `gpt-3.5-turbo-instruct` We were not talking about that model and I'm 99.999% sure you do not use that model. You might as well mention text-davinci-003 and all the legacy models, you're muddying the waters. > b) Even the chat tuned version does completions, if you go via Azure and use ChatML you can confirm it for yourself. They trained the later check…
Earlier quoted context omitted.
> a) gpt-3.5-turbo has a completion endpoint version as of June: `gpt-3.5-turbo-instruct` We were not talking about that model and I'm 99.999% sure you do not use that model. You might as well mention text-davinci-003 and all the legacy models, you're muddying the waters. > b) Even the chat tuned version does completions, if you go via Azure and use ChatML you can confirm it for yourself. They trained the later check…
You have some stuff to worth through, and I wish you the best with that.
I really want that Azure information and whether prefilling works there as it does with Claude or not. Can you provide that at least before you walk away?
LLMs are trained on the entire internet and more.
I want a model that just gives me the answer with whatever it knows instead of playing pseudoethics.
Sure it can say this is dangerous “don’t do this at home” but let me be the judge of it.
Earlier quoted context omitted.
I’m mostly a curious dev but OpenAI hasn’t stopped me from learning and growing on their platform.
That may be because they have a lot more budget and the support of one of the largest cloud providers on earth. Offering free GPU compute to millions of people is really not an easy or cheap task.
Earlier quoted context omitted.
OpenAI just had to pause signups after demo day because of capacity issues. They also switched to making users pay in advance for usage instead of billing them after.
They aren't switching anything with payments. Bad rumor amplified by social contagion and a 100K:1 ratio of people talking about it to people building with it.
Great but it stills leaves the problem of accessing it. I have never heard back on access from Anthropic's website and still waiting on the request through Bedrock. Not sure the success rate of others but it seems impossible as a business to get access to the API. Not a downplay on their announcement but with how difficult it seems to get API access its hard to see the improvement.
I requested access through Bedrock and had it minutes later. It's an automated process.