A quick OpenAI-o1 preview BOTEC for additional emissions from a sort of Leopold scenario ~2030, assuming energy is mostly provided by natural gas, since I was kinda curious. Not much time spent on this and took the results at face value. I (of course?) buy that emissions don’t matter in short term, in a world where R&D is increasingly automated and scaled.
Phib:
Say an additional 20% of US electricity was added to our power usage (e.g. for AI) over the next 6 years, and it was mostly natural gas.
Also, that AI inference is used at an increasing rate, say 100Million H100s equivalent, increasing from today’s level to 100M over the next 6 years, and it’s more or less the same as today’s energy breakdown, although with more natural gas over time.
What do the emissions from such a build out of natural gas look like?
The emissions from this build-out of natural gas over the next six years would be significant. Specifically:
Total Additional Emissions Over Six Years: Approximately 1.136 billion metric tons of CO₂.
Average Annual Emissions Increase: About 189 million metric tons of CO₂ per year.
Percentage of Current U.S. Emissions: This represents an approximate 2.9% increase over the current annual U.S. greenhouse gas emissions.
These emissions result from the increased natural gas usage required to meet the additional electricity demand—both from the general 20% increase in electricity consumption and the substantial growth in AI inference workloads powered by the equivalent of 100 million NVIDIA H100 GPUs.
Phib:
Imagine there is a similar buildout in China, if not larger, how do the emissions from all of the above (within some confidence interval) place us environmentally within 2 years after 2030 of such a buildout and increase in emissions? Within 10 years? Considering a more or less constant rate of emissions thereafter for each.
Conclusion
The combined emissions from the U.S. and China’s buildouts would significantly impact the global carbon budget and environmental goals:
By 2032 (Two Years After 2030):
Additional Emissions: Approximately 2.44 billion metric tons of CO₂.
Impact: Uses about 0.42% of the remaining carbon budget for limiting warming to 1.5°C.
By 2040 (Ten Years After 2030):
Additional Emissions: Approximately 12.21 billion metric tons of CO₂.
Impact: Consumes about 2.1% of the carbon budget.
Cumulative Impact by 2040:
Total Additional Emissions: Around 19.54 billion metric tons of CO₂.
Percentage of Carbon Budget: Approximately 3.37%.
Environmental Implications:
Increased Difficulty in Meeting Climate Targets: The additional emissions make it more challenging to stay within the carbon budgets necessary to limit global warming to 1.5°C or even 2°C.
Accelerated Climate Change Effects: Higher emissions could lead to more severe climate impacts, such as extreme weather events, sea-level rise, and ecosystem disruptions.
Final Note:
These estimates are subject to uncertainties due to potential changes in technology, policy, and economic factors. Proactive measures, such as investing in renewable energy and improving energy efficiency, could mitigate some of these emissions. However, without significant efforts to reduce reliance on fossil fuels, the environmental impact will be substantial and pose a serious challenge to global climate goals.
Final Phib note, perhaps inference energy costs may be far greater than assumed above, I don’t imagine a GPT-5, GPT-6, that justify further investment, not also being adopted by a much larger population proportion (maybe 1 billion, 2 billion, instead of 100 million).
A quick OpenAI-o1 preview BOTEC for additional emissions from a sort of Leopold scenario ~2030, assuming energy is mostly provided by natural gas, since I was kinda curious. Not much time spent on this and took the results at face value. I (of course?) buy that emissions don’t matter in short term, in a world where R&D is increasingly automated and scaled.
Phib: Say an additional 20% of US electricity was added to our power usage (e.g. for AI) over the next 6 years, and it was mostly natural gas. Also, that AI inference is used at an increasing rate, say 100Million H100s equivalent, increasing from today’s level to 100M over the next 6 years, and it’s more or less the same as today’s energy breakdown, although with more natural gas over time.
What do the emissions from such a build out of natural gas look like?
[Reasoning available here: https://chatgpt.com/share/672ed183-7c3c-800d-ab0e-d08020d072c7]
**Answer:
The emissions from this build-out of natural gas over the next six years would be significant. Specifically:
Total Additional Emissions Over Six Years: Approximately 1.136 billion metric tons of CO₂.
Average Annual Emissions Increase: About 189 million metric tons of CO₂ per year.
Percentage of Current U.S. Emissions: This represents an approximate 2.9% increase over the current annual U.S. greenhouse gas emissions.
These emissions result from the increased natural gas usage required to meet the additional electricity demand—both from the general 20% increase in electricity consumption and the substantial growth in AI inference workloads powered by the equivalent of 100 million NVIDIA H100 GPUs.
Phib: Imagine there is a similar buildout in China, if not larger, how do the emissions from all of the above (within some confidence interval) place us environmentally within 2 years after 2030 of such a buildout and increase in emissions? Within 10 years? Considering a more or less constant rate of emissions thereafter for each.
Conclusion The combined emissions from the U.S. and China’s buildouts would significantly impact the global carbon budget and environmental goals:
By 2032 (Two Years After 2030):
Additional Emissions: Approximately 2.44 billion metric tons of CO₂. Impact: Uses about 0.42% of the remaining carbon budget for limiting warming to 1.5°C. By 2040 (Ten Years After 2030):
Additional Emissions: Approximately 12.21 billion metric tons of CO₂. Impact: Consumes about 2.1% of the carbon budget. Cumulative Impact by 2040:
Total Additional Emissions: Around 19.54 billion metric tons of CO₂. Percentage of Carbon Budget: Approximately 3.37%.
Environmental Implications:
Increased Difficulty in Meeting Climate Targets: The additional emissions make it more challenging to stay within the carbon budgets necessary to limit global warming to 1.5°C or even 2°C. Accelerated Climate Change Effects: Higher emissions could lead to more severe climate impacts, such as extreme weather events, sea-level rise, and ecosystem disruptions.
Final Note:
These estimates are subject to uncertainties due to potential changes in technology, policy, and economic factors. Proactive measures, such as investing in renewable energy and improving energy efficiency, could mitigate some of these emissions. However, without significant efforts to reduce reliance on fossil fuels, the environmental impact will be substantial and pose a serious challenge to global climate goals.
Final Phib note, perhaps inference energy costs may be far greater than assumed above, I don’t imagine a GPT-5, GPT-6, that justify further investment, not also being adopted by a much larger population proportion (maybe 1 billion, 2 billion, instead of 100 million).