zlacker

Ecosystem around chat GPT is the differentiator that Meta and Mistral can’t beat – so I’d say that Altman is more relevant today than ever. And, for example, if you’ve read Mistral’s paper – I think you would agree that it’s straightforward to replicate similar results for every other major player. Replicating ecosystem is much harder.

Performance is never a complete product – neither for Apple, nor for Open AI (its for-profit part).

>>ohcmon+(OP)
If you really need such an ecosystem, then you can build one right away, like Kagi Labs and Phind did. In the case of Kagi, no GPT is involved; in the case of Phind, GPT-4 is still vital, but they are closing the gap with their cheaper and faster LLaMA-2 34B-based models.

> Performance is never a complete product

In the case of GPT-4, performance - in terms of the quality of generation and speed - is the vital aspect that still holds competitors back.

Google, Microsoft, Meta, and countless research teams and individual researchers are actually responsible for the success of OpenAI, and this should remain a collective effort. What OpenAI is doing now by hiding details of their models is actually wrong. They stand on the shoulders of giants but refuse to share these days, and Altman is responsible for this.

Let us not forget what OpenAI was declared to stand for.

>>pk-pro+K8
Under ecosystem I mean people using ChatGPT daily on their phones and browsers, developers (and now virtually anyone) writing extensions. For most of the world all of the progress is condensed at chat.openai.com, and it will be only harder to beat this adoption.

Tech superiority might be relevant today, but I highly doubt it will stay the same for a long time even if openai continues to hide details (which I agree is bad). We could argue about the training data, but we have so much publicity available so that is not an issue as well.