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

New models and developer products

openai.com

Post reply on HN
Print view View original

251–260 of 561 posts

Re: New models and developer products

#251

Post by skybrian »

simonw wrote: post #3

The new assistants API looks both super-cool and (unfortunately) a recipe for all kinds of new applications that are vulnerable to prompt injection.

Yes. Hopefully, sandboxing limits the damage somewhat, but it doesn't help if you put any private docs in the sandbox.

Also, the limitations of the Code Assistant tool's server-side Python sandbox aren't described in their API docs. In particular, when does the sandbox get killed? Anyone know? If they're similar to the Code Assistant tool in ChatGPT, then it kills your sandbox within an hour or so (if you go to lunch) which is a crappy user experience.

Running the sandbox on the user's machine seems like a better approach. There's no reason to kill the sandbox if it's not using any server-side resources. Maybe the function-calling API would be useful for that, somehow?

The most immediately useful thing is the price cut, though.

Re: New models and developer products

#252

Post by charlie0 »

sharemywin wrote: post #144
gumballindie wrote: post #32

Earlier quoted context omitted.

And just like amazon they will compete with their own customers. They are miles ahead in this regard as well since they basically take everyone’s digital property and resell it.

don't hate the player hate the game.

and if you can't beat them, join them.

Re: New models and developer products

#254

Post by kortilla »

vsareto wrote: post #85
minimaxir wrote: post #4

Most of the products announced (and the price cuts) appear to be more about increasing lock-in to the OpenAI API platform, which is not surprising given increased competition in the space. The GPTs/GPT Agents and Assistants demos in particular showed that they are a black box within a black box within a black box that you can't port anywhere else. I'm mixed on the presentation and will need to read the fine print on…

>The GPTs/GPT Agents and Assistants demos in particular showed that they are a black box within a black box within a black box that you can't port anywhere else. This just rings hollow to me. We lost the fights for database portability, cloud portability, payments/billing portability, and other individual SaaS lock-in. I don't see why it'll be different this time around.

> We lost the fights for database portability, cloud portability, payments/billing portability, and other individual SaaS lock-in.

No we didn’t. There are viable on-prem alternatives or cross cloud alternatives for everything popular on the cloud.

Many companies did choose to hand their destiny over to cloud providers but lots didn’t.

Re: New models and developer products

#255

Post by skybrian »

burcs wrote: post #8
simonw wrote: post #3

The new assistants API looks both super-cool and (unfortunately) a recipe for all kinds of new applications that are vulnerable to prompt injection.

Do you see a way around prompt injection? It feels like any feature they release is going to be susceptible to it.

One approach might be to redact sensitive parts of the input, replacing private data with tokens. Then substitute the tokens back again in the output.

But this only works if the sensitive data isn't needed for inference and you have a reliable way of detecting it.

Re: New models and developer products

#257

Post by quinncom »

danielbln wrote: post #149
m3kw9 wrote: post #141

Earlier quoted context omitted.

How does this absolve vectordbs

It doesn't, but semantic search is a lot less relevant if you can squeeze 350 pages of text into the context.

OpenAI charges for all those input tokens. If an app requires squeezing 350 pages of content in every request is going to cost more. Vector DB still relevant for cost and speed.

Re: New models and developer products

#258

Post by zizee »

In people's experience with these sorts of tools, have they assisted with maintainance of codebases? This might be directly, or indirectly via more readable, bette organized code.

The reason I ask is that these tools seem to excel in helping to write new code. In my experience I think there is an upper limit to the amount of code a single developer can maintain. Eventually you can't keep everything in your head, so maintaining it becomes more effort as you need to stop to familiarize yourself with something.

If these tools help to write more code, but do not assist with maintainance, I wonder if we're going to see masses of new code written really quickly, and then everything grinds to a halt, because no one has an intimate understanding of what was written?

Re: New models and developer products

#259

Post by ignite2 »

anotherpaulg wrote: post #83
tornato7 wrote: post #78

According to [1], the new gpt-4-1106-preview model should be available to all, but the API is telling me "The model `gpt-4-1106-preview` does not exist or you do not have access to it." Anyone able to call it from the API? 1. https://help.openai.com/en/articles/8555510-gpt-4-turbo

Same. I am eager to run my code editing benchmark [1] against it, to compare it with gpt-4-0314 and gpt-4-0613. Edit: Ha, I just re-read the announcement [2] and it says 1pm in the 5th sentence: We’ll begin rolling out new features to OpenAI customers starting at 1pm PT today. [1] https://aider.chat/docs/benchmarks.html [2] https://openai.com/blog/new-models-and-developer-products-an...

"begin".

Other comments says this can take days to get to everyone.

Re: New models and developer products

#260

Post by btbuildem »

bluecrab wrote: post #152
burcs wrote: post #8

Earlier quoted context omitted.

Do you see a way around prompt injection? It feels like any feature they release is going to be susceptible to it.

Use an llm to evaluate the input and categorise it.

Yup -- it's as simple as that.
Post reply on HN