Interesting note here on how OpenAI model aliases are selected
LLMS
-

New AI models with reasoning capabilities unveiled by major researchers
By
–
.
@FT splash on a new generation of models with partial “reasoning” capabilities. W/
@CristinaCriddle ft @bradlightcap
, @ylecun and @jpineau1 -
Prompt Engineering Strategies for GPT and Claude Models
By
–
I've not tried fine-tuning any models at all – I've been focusing on figuring out how to best prompt the larger models like gpt-3.5-turbo or claude-3-haiku, mainly through figuring out the best examples to give them
-
Updated Gemini Pro Now Available on Poe Platform
By
–
You can try the updated Gemini Pro at https://
poe.com/Gemini-Pro and on all Poe apps. (4/4) -
Google Upgrades Gemini Pro with Enhanced Conversational Abilities
By
–
We’ve also added an upgraded version of the original Gemini Pro. This bot has been fine-tuned with a more conversational personality, and features quality improvements in areas such as reasoning, math, latency, storytelling, and summarization. (3/4)
-
Gemini 1.5 Pro Now Available on Poe with Multiple Versions
By
–
Gemini 1.5 Pro supports text, image, and video input, with text output. It is available today on web and across all Poe apps in three versions: Gemini 1.5 Pro https://
poe.com/Gemini-1.5-Pro, 128k https://
poe.com/Gemini-1.5-Pro
-128k
…, and 1M https://
poe.com/Gemini-1.5-Pro
-1M
…. (2/4) -

Google Launches Gemini 1.5 Pro with Million Token Context
By
–
Now on Poe: Gemini 1.5 Pro! This powerful new multimodal model from Google introduces an industry-leading context window of 1 million tokens (~700,00 words) with near-perfect retrieval, enabling complex tasks that require long-context understanding. (1/4)
-
LLMs Lack Self-Knowledge Causing Critical Mistakes
By
–
The fact that LLMs lack self-knowledge causes a lot of mistakes
-
GPT-4 Improvements Lack Transparency and Release Notes
By
–
As is usual with AI, a “majorly improved” GPT-4 model comes with no real changelogs or release notes. It’s going to better at many things and worse in some other things and also different in some other way you aren’t expecting. Or that might just be in your head. AI is weird.
-
GPT-4 Turbo Model Significantly Improved in API
By
–
Majorly improved GPT-4 Turbo model available now in the API and rolling out in ChatGPT.