Many people are reporting errors in the playground
> Failed to update assistant: UserError: Failed to index file
New models and developer products
441–450 of 561 posts
Re: New models and developer products
#442With the assistant API, am I wrong or is it now much cheaper to actually use the API instead of the web Interface? $20 would cover a lot of interactions with the API, and since it’s now also doing truncation / history augmentation the API would have pretty much the same functionality. Thoughts?
Re: New models and developer products
#443In 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 m…
My open source ai coding tool aider is unique in that it is designed to work with existing code bases. You can jump into an existing git repo and start aaking for changes, new features, etc. https://github.com/paul-gauthier/aider It helps gpt understand larger code bases by building a "repository map" based on analyzing the abstract syntax tree of all the code in the repo. This is all built using tree-sitter, the sam…
How do you manage token limits when sending large amounts of code structure to OpenAI?
Re: New models and developer products
#444Something I'd really like to see is GitHub integration. Point it at a git repository, have it analyze it and suggest improvements, provide a high level break down, point me towards the right place to make changes.
Re: New models and developer products
#445In 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 m…
My open source ai coding tool aider is unique in that it is designed to work with existing code bases. You can jump into an existing git repo and start aaking for changes, new features, etc. https://github.com/paul-gauthier/aider It helps gpt understand larger code bases by building a "repository map" based on analyzing the abstract syntax tree of all the code in the repo. This is all built using tree-sitter, the sam…
Thanks a lot for doing this project. Your blog post got me excited.
Re: New models and developer products
#446If I had no contact with society from the 29th of November 2022 (the day before ChatGPT was released according to Wikipedia) and came back today to see the OpenAI keynote I would have lost my mind. The progress and usefulness of these products is absolutely incredible.
I'm sorry, what breakthrough feature did we see here?
- Code interpreter, function calling were already possible on any sufficiently advanced LLM that could follow instructions well enough to output tokens in a rigidly parseable format, which could then be fed into a parser, and its output fed back to the LLM. It was clunky to do with online APIs like ChatGPT, but still eminently possible.
- Custom chatbots were easy to build before, and services to build them (like Poe.com) existed before.
- Likewise outputting JSON just requires a good instruction following AI, that can output token probabilities, along with a schema validator that always picks a token that results in schema-conforming JSON
- GPT4-128k seems to be revolutionary, but Claude-100k already existed, and considering LLM evaluation is quadratic wrt context size, they are probably using some tricks to extend the context, they are not 'full' tokens (I'd be happy to be proven wrong). While having a huge context is useful, for coding, a 8k context can be enough with some elbow grease (like filling the context with a 2-3 deep recursive 'Go To Definition' for a given symbol), so that the AI receives the right context.
- Dall-E 3 seems to be the most revolutionary, but after playing with it, it has much improved compositional ability over SD, but it's still prone to breakdowns
Overall I feel like todays announcements were polish and refinement over last year's bombshell breakthroughs.
Re: New models and developer products
#447Something I'd really like to see is GitHub integration. Point it at a git repository, have it analyze it and suggest improvements, provide a high level break down, point me towards the right place to make changes.
This shouldn’t be too difficult, the api allows writing such a tool and with the „assistant API“ it should hopefully be able to put attention on the right parts…
So: git clone -> system prompt -> add files of repo to messages -> get answer…
Re: New models and developer products
#448Earlier quoted context omitted.
You’re talking about the issue as if it weren’t your posts, your pictures, or content of artists you are into. This isn’t a ”copyright risk“, it’s a Silicon Valley corporation getting away with declaring copyright just… obsolete.
They are my content, actually, from the last ~15 years of being on the internet. I don't care about it personally, and even if I did it is really obviously fair use so even if I find it objectionable I don't get to actually legally compel someone to stop.
What on earth is fair use about a public company deriving its whole valuation from the processing of content taken from the internet without any regard for licensing, or robots.txt rules??
The technology is cool, I get it. But saying ”I don’t mind, they can use my content“ is on par with ”I don’t need privacy, I have nothing to hide“ in terms of statement quality.
Re: New models and developer products
#449I sure hope this carrot thrown down to the masses is not going to slow down open models development.
When the deal looks too good to be true. You're not a customer. You're a product/a resource to mine. In case of (not-at-all)OpenAI this is doing two things. Killing competition by running their services below costs(this used to be illegal even in the USA) and gathering massive amounts of human generated question/ranking data. I'm not sure about others, but I'm getting quite a few of these "which answer is better" prompts.
Why do I hope for the continued progress in open models even if this is so much more powerful/cheap to run? Because when you're not a customer, but a product the inevitable enshittification of the service always ensues.
Re: New models and developer products
#450Whisper V3 is released! https://github.com/openai/whisper/commit/c5d42560760a05584c1... Looks like it's just a new checkpoint for the large model. It would be nice to have updates for the smaller models too. But it'll be easy to integrate with anything using Whisper V2. I'm excited to add it to my local voice AI ( https://www.microsoft.com/store/apps/9NC624PBFGB7 ) I assume ChatGPT voice has been using Whisper V3 and…
Too bad they didn't upgrade Whisper API yet. Can't wait to make it available in https://whispermemos.com
If you add an Android version that I could activate from my lock screen, you'll have another customer.