#ChatGPT estimates the resource usage of models like GPT-3 and GPT-4 running in a multi-tenant environment.
As expected, ChatGPT is incapable of self-introspection, but it's surprisingly able to suggest a simple workaround 😲
#ChatGPT estimates the resource usage of models like GPT-3 and GPT-4 running in a multi-tenant environment.
As expected, ChatGPT is incapable of self-introspection, but it's surprisingly able to suggest a simple workaround 😲
Please check the chat log for possible hallucinations.
You may notice a "minor" issue with the GPT's estimate:
1024 * 96 * (12288 * 49) = 5,871,583,232 bytes
The correct result would be 59,190,018,048 - a factor 10 larger.
I have no idea where it pulled that result from, but we already knew that math wasn't ChatGPT's forte 😂
Bobinas P4G is a social network. It runs on GNU social, version 2.0.1-beta0, available under the GNU Affero General Public License.
All Bobinas P4G content and data are available under the Creative Commons Attribution 3.0 license.