first forvay into the new Siri

14 views
Skip to first unread message

Robert Brown (RLBrown)

unread,
Jun 9, 2026, 4:12:20 PM (13 days ago) Jun 9
to sv...@googlegroups.com

Hello SVMUG members and Friends,


I have started experimenting with the new Siri. I am operating under heavy limitations. While I have macOS 27 developer beta and the new Siri is active, my Mac Studio runs an M1 chip. It can not support “on-device” models. This means that most queries to Siri are sent to the Siri model on the Apple servers, I am not sure of the correct branding for these servers. I call them Private Cloud Compute (PCC).


I made a query that requires server resources, shown at the bottom of this email. I checked and found that no external model besides Siri was used. This should give a reasonable expectation for what the knowledge component of Siri can do.


In that regard, I note that Siri's settings still seem to allow only ChatGPT as an extension. Perhaps the ability to select others, most especially Gemini, will come in a later update.


The references used by Siri were credible, and links were provided.


Here is the query and response.


Query prompt: Acting as a physicist reading just credible published papers, please evaluate the current state of fusion energy generation, including estimates of when this will have an appreciable impact. Include references.


Response:


The current state of fusion energy generation is characterized by significant scientific breakthroughs, particularly the achievement of net energy gain in laboratory conditions, but it remains in the developmental phase with major engineering and economic challenges to overcome before commercial viability. While some private companies project commercial fusion power by the early 2030s, most experts and government roadmaps estimate that fusion will not have an appreciable impact on the global energy grid until the 2040s or later.


KEY SCIENTIFIC AND ENGINEERING CHALLENGES


Despite recent progress, several fundamental hurdles must be addressed to transition fusion from experimental success to a practical power source.


  • Sustained Energy Gain The National Ignition Facility (NIF) has achieved a fusion energy gain factor (Q) of up to 2.4, meaning the fusion reaction produced more energy than the lasers delivered to the fuel target. However, this does not account for the total energy required to power the entire facility, which is hundreds of times greater. For a power plant to be viable, the total energy output must exceed the total energy input by a factor of 10 or more.
  • High Repetition Rates Current experiments like NIF can only fire once per day. A commercial power plant would need to repeat the fusion process at a rate of 10 or more times per second, which requires developing new laser and target delivery systems.
  • Advanced Materials Reactor components must withstand extreme conditions, including temperatures of over 180 million degrees Fahrenheit and intense neutron radiation that can degrade materials over time. Developing durable, radiation-resistant materials is a critical engineering challenge.
  • Fuel Cycle and Tritium Supply The most feasible fusion reaction uses deuterium and tritium, isotopes of hydrogen. Tritium is scarce and radioactive, and a commercial fusion industry would require a self-sufficient fuel cycle where the reactor itself breeds its own tritium.
  • Plasma Control In magnetic confinement fusion, the superheated plasma must be precisely controlled and contained for long periods to sustain the reaction. This is a complex task, though AI is showing promise in predicting and suppressing plasma instabilities.

MAJOR APPROACHES TO FUSION


Two primary scientific approaches are being pursued to achieve controlled fusion.



APPROACH



DESCRIPTION



KEY FACILITIES & COMPANIES



Magnetic Confinement Fusion (MCF)



Uses powerful magnetic fields to confine and heat a plasma of fuel to fusion temperatures.



ITER, Commonwealth Fusion Systems, Helion Energy



Inertial Confinement Fusion (ICF)



Uses powerful lasers to compress and heat a small fuel pellet, initiating fusion.



National Ignition Facility (NIF), General Fusion, TAE Technologies



TIMELINES FOR IMPACT


Estimates for when fusion energy will have a significant impact on the power grid vary widely between optimistic industry projections and more conservative expert assessments.


  • Industry Projections Many private fusion companies, driven by significant investment, are targeting the early 2030s for the first grid-connected pilot plants. Some, like Helion Energy, have announced contracts to deliver electricity as early as 2028.
  • Expert and Government Assessments Most government roadmaps and independent experts are more cautious, predicting that a fusion pilot plant capable of producing net electricity will be operational between 2035 and 2040. A significant commercial rollout is not expected until the 2040s or 2050s. The long-standing joke that fusion is "always 30 years away" reflects the historical difficulty of predicting its timeline.

ECONOMIC AND SOCIETAL POTENTIAL


If the technical challenges are overcome, fusion energy offers several compelling advantages that could make it a transformative technology.


  • Abundant Fuel The primary fuels, deuterium and tritium, can be extracted from seawater, providing a virtually limitless energy source.
  • Clean Energy Fusion is a carbon-free energy source that does not produce long-lived radioactive waste, unlike nuclear fission.
  • Reliable Power Fusion power plants could provide a constant, "firm" source of electricity that is not dependent on weather conditions, making them a valuable complement to intermittent renewables like solar and wind.
  • Economic Value Studies suggest that the availability of fusion power could reduce the global cost of decarbonizing the electricity system by trillions of dollars.

Are you more interested in a specific technical approach, the economic outlook, or the regulatory challenges?



Robert Lawson Brown

mail

                                                           

Jose Francisco Medeiros

unread,
Jun 9, 2026, 4:25:15 PM (13 days ago) Jun 9
to sv...@googlegroups.com
That's cool Robert!


--
You received this message because you are subscribed to the Google Groups "SVMUG" group.
To unsubscribe from this group and stop receiving emails from it, send an email to svmug+un...@googlegroups.com.
To view this discussion visit https://groups.google.com/d/msgid/svmug/0CCA9A9C-0AD5-467A-907F-F236D2705BCB%40rlbrown.org.
Reply all
Reply to author
Forward
0 new messages