The ChatGPT app is broken on IOS after the update. Image generation and code analysis no longer work
New models and developer products
291–300 of 561 posts
Re: New models and developer products
#292Earlier quoted context omitted.
I haven't been paying attention, why are embeddings not needed anymore?
Embedding is poor man's context length increase. It essentially increases your context length but with loss. There is a cost argument to make still, embedding-based approach will be cheaper and faster, but worse result than full text. That being said, I don't see how those embedding startups compete with OpenAI, no one will be able to offer better embedding than OpenAI itself. It is hardly a convincing business. The…
For embeddings specifically, there are multiple open source models that outperform OpenAI’s best model (text-embedding-ada-002) that you can see on the MTEB Leaderboard [1]
> embedding-based approach will be cheaper and faster, but worse result than full text
I’m not sure results would be worse, I think it depends on the extent to which the models are able to ignore irrelevant context, which is a problem [2]. Using retrieval can come closer to providing only relevant context.
Re: New models and developer products
#293Any idea what the deal is with what looks like the Singapore coats of arms here? https://www.youtube.com/live/U9mJuUkhUzk?si=H8yYWiuJvaxVhIsV...
Re: New models and developer products
#294In 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…
We are doing this for API-Testing now. You should check out our website https://ai.stepci.com
piece of feedback: it's weird to have a drop-down on "OpenAPI Links" when there are no other options.
Re: New models and developer products
#295I just released a new version of my LLM CLI tool with support for the new GPT-4 Turbo model: https://llm.datasette.io/en/stable/changelog.html#v0-12 You can install it like this: pipx install llm Then set an API key: llm keys set openai Then run a prompt through GPT-4 Turbo like this: llm -m gpt-4-turbo "Ten great names for a pet walrus" # Or a shortcut: llm -m 4t "Ten great names for a pet walrus" Here's a one-liner…
[dead]
Re: New models and developer products
#296For all the naysayers in the comments, the elephant in the room that no one quite wants to admit, is that GPT4 is still far better than everything else out there
Grok? Just kidding
Re: New models and developer products
#297Earlier quoted context omitted.
Mistral + 2 weeks of work from the community. Not as good, but private and free. It will trail OpenAI by 6-12 months in capabilities.
OpenAI offering 128k context is very appealing, however. I tried some Mistral variants with larger context windows, and had very poor results… the model would often offer either an empty completion or a nonsensical completion, even though the content fit comfortably within the context window, and I was placing a direct question either at the beginning or end, and either with or without an explanation of the task and…
Open researchers are trying to shrink and speed up 138K models e.g. YaRN https://github.com/jquesnelle/yarn
It's very compelling and opens up a lot of use cases, so I've been keeping an eye out for advancements. However, inferencing on 4xA100s would be the target today for YaRN and 128K to get a reasonable token rate on their version of Mistral.
Re: New models and developer products
#298You can now [1] pay from $2 to $3 million to pretrain custom gpt-n model. This has gone unnoticed but seems really neat. Provided that a start-up has enough money spend on that, it would certainly give competitive advantage. [1] https://openai.com/form/custom-models Edit: forgot to put the link
Well it won’t because they’ll use the model you paid for and take your customers.
How do you square this with OpenAI's assertion that they never use data from enterprise customers for their own training? Are you suggesting they're lying?
Re: New models and developer products
#299Earlier quoted context omitted.
It's a good strategy. For me, avoiding the moat means either a big drop in quality and just ending up in somebody elses moat, or a big drop in quality and a lot more money spent. I've looked into it and maybe the most practical end-to-end system for owning my own LLM is to run a couple of 3090s on a consumer motherboard at substantial running cost to keep them up 24/7 and that's not powerful enough to cut it and rath…
Everybody's got their own calculus about how competitive their space is and what this tech can do for them, but some might be best off dancing around lock-in by being careful about what they use from OpenAI and how tightly they integrate with it. This is very early in the maturity cycle for this tech. The options that will be available for private inference and fine tuning, for cloud-gpu/timeshare inference and fine…
"What looks like squeezing value out of OpenAI today might look a lot like technical debt and frustrating lock-in a year from now."
Just wanted to highlight this as such a great, concise way to look at the Buy vs Build with pretty much any cloud service, thanks!
Re: New models and developer products
#300Every day this video ages more and more poorly [1]. categories of startups that will be affected by these launches: - vectorDB startups -> don't need embeddings anymore - file processing startups -> don't need to process files anymore - fine tuning startups -> can fine tune directly from the platform now, with GPT4 fine tuning coming - cost reduction startups -> they literally lowered prices and increased rate limits…
There is not much info about retrieval/RAG in their docs at the moment - did you find any example on how is the retrieval supposed to work and how to give it access to a DB?