Recent content by RyanMorrison

Some nice prompting work. The images look good. I am still impressed when AI gets text on images right - I sugggest trying Ideogram. It’s very good at legible text on images.

Jumping on this much later but you can use --cref create your first character then for each subsequent character type --cref and the url of the image to the first character. Use --cw [number from 1-100] to set how closely you want it to reflect the first. 100 is identical.

I'm working on the premium comparison now — hopefully go live in a couple of weeks. One of the big advantages of ChatGPT is being able to set custom instructions that remain across all chats, it is particularly useful as you say for things like meal planning. I'm also reviewing Claude 3 Pro to...

Yes. That will be coming in the next couple of weeks. I've already started working on it. I will also do a comparison with Claude 3 soon, now that the new model has launched and claims to beat GPT-4 in key benchmarks.

Gemini does have a big refusal problem, particularly for things that are region specific like translation and image creation. This should go away as Google rolls it out more widely.

That’s interesting. I have found that Gemini is more consistently responsive. I’ll be testing the pro versions over the next few weeks

The word Grok dates back to the early 60s, first coined in Heinlein's Stranger in a Strange Land. It had multiple meanings, one of which was to understand — hence the fascinating with the word among the emerging tech scene over the next few decades. The AI chip/platform Groq actually predates...

I left all questions to Claude 2. It determined what to ask each of the two chatbots based on things AI find difficult or non standard. This is also not a scientific analysis or benchmarking exercise - which is why I also made subjective decisions. In the end I still think Bard won, even if...

Yes. Gemini comes in three forms Ultra, Pro and Nano Ultra is equivalent to GPT-4 Pro to GPT-3.5 And Nano is a model running locally on Android It was Pro that Google integrated with Bard See my reporting here...

Why? Google says Bard with Gemini Pro is equal in capability to GPT3.5. It won't be comparable to GPT-4 until next year when Bard Advanced launches with Gemini Ultra.

We don't actually know if that is the case yet. Also many of those benchmark victories required multiple shots and chained prompts. I will do a side-by-side comparison between GPT-4 and Gemini Ultra when Gemini Ultra finally launches next year.

Unfortunately not yet. I've written several stories on Gemini and the version included with Bard TODAY is Gemini Pro, which Google says is roughly equivalent to GPT-3.5. This is the year old model that powers the free version of ChatGPT. Next year Google is launching Bard Advanced which is...

I could try it with Llama 2 or Mistral. I have both running locally on my computer

It was talking about Florida not Hawaii

The reason for comparing the free version of ChatGPT to Bard with Gemini Pro is because Google says it performs on par with GPT-3.5, the model that powers the free version of ChatGPT. Comparing it to GPT-4 would be unfair. However when Bard Advance launches in the new year I will then compare...