In particle physics we usually use these terms which will be at any proposal. This is an interesting textbook definition of false positives when you have list that is using too common words.
- Minimum "Biased" data
- "Discrimination" or "Discriminatory" variables
- Phase space "excluded"
- "Inclusion" of data/variable/anything
- "inequality" -> wow bell's inequality and all this theory work about inequalities will be triggered
These are just example that came into my mind from quick thought and skimming. I'm pretty sure that this will have much worst false positive rate. I would really be surprised if the vast majority if not all of projects get flagged. I'm also sure that 100% of statistics work or project heavily reliant on statistics (probably everything else too) will be flagged.
You're not wrong about the words not being banned, but that's not what the person you're responding to claimed.
I'll also note that being flagged for further scrutiny can effectively end a project that requires disbursement of funds in a timely manner. Ask me how I know, and I'll tell you that I was looking for work last week, because the projects I work on would not have been able to pay me next month if the executive order had not been rescinded. This isn't my speculation, it's what we were told by leadership. These projects are not at all DEI-related, but a shotgun approach to halting disbursal until we're convinced otherwise would have caused a lot of projects to go tits up in the interim. Grant-funded science projects generally do not have huge cash reserves to pay employees until the money spigot turns on again. So, applying a filter blacklist can be very destructive, just by creating temporary false positives.
The words searched are so common that it could literally flag a sizeable portion of all of science and such flags are liable if the trend continues to be handled by political hacks with zero expertise and expansive targets for cuts.
Heavy collateral damage is incredibly likely.
Also research with the wrong ideological underpinning can't violate anti-discrimination laws even if one imagines erroneously that application of same in hiring would despite prior supreme court findings.
Lastly over zealous punative punishment of lawful speech leading to aggressive self censorship is a entirely legitimate concern.
The logical result is suppressing the sciences. It is in fact the very same political correctness oft decried by nazis and bigots weaponized against everyone who isn't a christian white male.
> Reading comprehension is shocking, not just in you but most people here. The post just said "can cause a grant to be pulled". That's entirely consistent with this list being a screening filter and somebody will look at what the grant/application is actually for.
Both the post and the comment you are replying to used the term "flagged". Best I can tell, they aren't claiming what you seem to think they are claiming.
That's true. I was really generally replying to other comments but put it on this one because it was quite specific. You're quite right, an internal flag isn't a ban.
Their reading comprehension is just fine. The whole point of directives like this is the arbitrary nature by which they can be enforced. When everything can be flagged for review by a political commissar...
In the last century, neither fascists or stalinists had any issue with banning 'Jewish' science, despite it having absolutely nothing to do with race. Because their goal was getting rid of the enemies of the administration.
Where is the government going to find all these censors with working minds? No American would consent to doing that unless their zeal had blinded them from something much more important than the compliance of a physics paper.
Have you tried windsrf ( or more questionable trae)? They seem to be cursor alternative. I would like to know how they would compare it terms of UX to cline and cursor which I did not use. Aider is nice but I didn't try it much because I used it with Gemini API and aider complained about more deviating too much. So probably not aider fault.
Regarding the third point. you are no longer required to have Mailspring ID for sometime now.
For me, what actually makes me not using it is because it does not support Exchange without IMAP support which my university disable. Otherwise it is the best UX/UI email client on Linux.
Oh! You're right. I suppose I just missed the fact that there's now a skip button/text on the set up screen. Thanks for the correction. And yea its Linux/cross-platform support is also one of the main reasons for why I use it.
I do also remember the part about Exchange not being supported if IMAP is disabled. I had the same issue when I tried to use it at a university, but luckily haven't needed that since. Not surprising to hear that it hasn't changed either.
It is actually interesting for people working in academia. I would like to test it but no way I can afford $200/m right now.
Can someone test it with this prompt.
"As a research assistant with comprehensive knowledge of particle physics, please provide a detailed analysis of next-generation particle collider projects currently under consideration by the international physics community.
The analysis should encompass the major proposed projects, including the Future Circular Collider (FCC) at CERN, International Linear Collider (ILC), Compact Linear Collider (CLIC), various Muon Collider proposals, and any other significant projects as of 2024.
For each proposal, examine the planned energy ranges and collision types, estimated timeline for construction and operation, technical advantages and challenges, approximate costs, and key physics goals. Include information about current technical design reports, feasibility studies, and the level of international support and collaboration.
Present a thorough comparative analysis that addresses technical feasibility, cost-benefit considerations, scientific potential for new physics discoveries, timeline to first data collection, infrastructure requirements, and environmental impact. The projects should be compared in terms of their relative strengths, weaknesses, and potential contributions to advancing our understanding of fundamental physics.
Please format the response as a structured technical summary suitable for presentation at a topical meeting of particle physicists. Where appropriate, incorporate relevant figures and tables to facilitate clear comparisons between proposals. Base your analysis on information from peer-reviewed sources and official design reports, focusing on the most current available data and design specifications.
Consider the long-term implications of each proposal, including potential upgrade paths, flexibility for future modifications, and integration with existing research infrastructure."
Hopefully helpful, happy to test others for you :)
--
Raw output
--
Understood. I will conduct a detailed technical analysis of next-generation particle collider projects, focusing on the Future Circular Collider (FCC), International Linear Collider (ILC), Compact Linear Collider (CLIC), Muon Collider proposals, and other significant initiatives.
The report will include:
- Planned energy ranges and collision types
- Estimated construction and operation timelines
- Technical advantages and challenges
- Approximate costs
- Key physics goals
- Review of technical design reports and feasibility studies
- International collaboration and support
- Comparative analysis on feasibility, cost-benefit, scientific potential, infrastructure needs, and environmental impact
- Long-term considerations, including upgrade paths and integration with existing facilities
The analysis will be formatted as a structured technical summary, suitable for presentation at a topical meeting of particle physicists, with comparative tables and figures where relevant.
I will update you when the report is ready.
# Next-Generation Particle Collider Projects: A Comparative Technical Analysis
## Introduction
High-energy physics is charting plans for new colliders to extend beyond the LHC and its High-Luminosity upgrade (HL-LHC). The discovery of the 125 GeV Higgs boson has motivated proposals for a dedicated “Higgs factory” lepton collider to study its properties with precision, as well as future energy-frontier machines to search for new physics. Several next-generation collider initiatives are under consideration internationally as of 2024. These include CERN’s proposed *Future Circular Collider (FCC)*, Japan’s *International Linear Collider (ILC)*, CERN’s *Compact Linear Collider (CLIC)*, various designs for a *Muon Collider*, China’s *Circular Electron-Positron Collider (CEPC)* and its successor *Super Proton-Proton Collider (SppC)*, among others. Each proposal differs in collision type (electron-positron, proton-proton, muon-muon, etc.), energy scale, technology, timeline, cost, and physics focus. This summary reviews each project’s key parameters – *planned energy ranges, collision types, timeline, technical advantages/challenges, cost, and physics goals* – based on technical design reports and feasibility studies. A comparative analysis then contrasts their *technical feasibility, cost-benefit, scientific potential for discoveries, timeline to first data, infrastructure needs, and environmental impact*, highlighting the relative strengths and weaknesses of each approach. We also discuss long-term implications such as upgrade paths, flexibility for future modifications, and integration with existing infrastructure.
(Citations refer to official reports and peer-reviewed sources using the format 【source†lines】.)
## Future Circular Collider (FCC) – CERN
- *Type and Energy:* The FCC is a *proposed 100 km circular collider* at CERN that would be realized in stages. The first stage, *FCC-ee*, is an electron-positron ($e^+e^-$) collider with center-of-mass energy tunable from ~90 GeV up to 350–365 GeV, covering the Z boson pole, WW threshold, Higgs production (240 GeV), and top-quark pair threshold (~350 GeV). A second stage, *FCC-hh*, would use the same tunnel for a proton-proton collider at up to *100 TeV* center-of-mass energy (an order of magnitude above the LHC’s 14 TeV). Heavy-ion collisions (e.g. Pb–Pb) are also envisioned. An *FCC-eh* option (electron-hadron collisions) is considered by adding a high-energy electron injector to collide with the proton beam. This integrated FCC program thus spans both *precision lepton* collisions and *energy-frontier hadron* collisions.
- *Timeline:* The conceptual schedule foresees *FCC-ee construction in the 2030s* and a start of operations by around *2040* (as the LHC/HL-LHC program winds down). According to the FCC Conceptual Design Report, an $e^+e^-$ Higgs factory could begin delivering physics in ~2040, running for 15–20 years. The *hadron collider FCC-hh* would be constructed subsequently (using the same tunnel and upgraded infrastructure), aiming for *first proton-proton collisions in the late 2050s】. This staged approach (lepton collider first, hadron later) mirrors the successful *LEP–LHC sequence*, leveraging the $e^+e^-$ machine to produce great precision data (and to build infrastructure) before pushing to the highest energies with the hadron machine.
...
Thank you very much for doing that. It is actually somehow impressive. It got a lot of big picture comparison and points correct. There are problem with some details but overall it does save some work for initial search process.
What I like is that it asked you before clarifying questions before but I wonder if it just generic. Because the prompt mentioned that this would be for "presentation at a topical meeting of particle physicists" but still asked its last question about
> Intended Audience: Should the analysis assume a general physics audience or a more specialized group of particle physicists?
Also probably expected but it didn't include or reference graphs/plots.
That also apply to the Multilingual tests they do. I wonder if the overall gain against Base GPT-4o is there. What even strange is that they spent about three pages talking about how hard they worked on making sure that the model doesn't answer questions about nuclear weapons or anything that seems unsafe in this regard. Which is funny because they even said that they do this although they didn't train on classified information and the knowledge it contains is from unclassified information.
Nuclear development is state actors game. If they want to do it they wouldn't need LLM to answer the questions. And most of the work is actually building the program and acquiring materials ..etc. And do all of these development while not make themselves detected by the world (which is impossible task).
But they spent less time and explanation on more important parts like coding performance.
I'm still reading the details, but my first thought is that I like that the competition is actually working in this situation. I hope that someday it will be more open from all actors. And that we don't make more polarized that it is now and don't focus on the geopolitical angle and make it the core issue. I know that this hope is far fetched and more ideal than most people would think. But as someone who really find these development interesting and would like LLMs to be more useful (and don't think too much about AGI as it is the fusion project of the Artificial Intelligence field).
This is far too soon after R1 to be a reaction. They were training this model before R1. If they stopped censoring the reasoning steps or (Yud forbid) open sourced it, that would be competition really working. But they won't.
Without going into the discussion about polarized points. I have some observations
1- NSF budget is about 10 billions, I always had in mind that it is much more. That's about 0.17% of the total federal budget. If we include DOE R&D funding and NIH we will get to 1%. This is the funding for most of research in science in the US. Seems like not a great area to achieve huge reduction in deficit.
2- Even if we ignore the whole point of DEI and say that we need to end support for some of the projects. You do take your time and evaluate projects that needs to take action. You don't stop all the funding and pause critical support for projects and cause huge problems on medium and long term. And it also hurt the reputation of the country and its competitiveness.
3- The current NSF director was actually appointed by the current setting president in his first term.
I fail to see why a scientist won’t be interested in the grant now. Maybe if you’re talking about some areas like social sciences, yes, but for everything else not much seems to have changed.
I have not been paid because my salary is funded by an NSF grant and they've shut down the payment system and cancelled payments. (It is still down.) I'm not in the social sciences, I'm in mathematics.
The instability this has created has me looking to leave academia as quickly as possible; I'm sure others in similar situations are having the same thoughts. This has wreaked havoc on all of academia.
Thank you for providing extra context! I can see why the unpredictability of the entire system could make people not even consider applying in the future.
Sorry to hear that this happened to you. I hope they will provide some way to sort this out soon.
It's all about stability and predictability. Science, like other forms of business, favors an environment without sudden regulatory changes. Sudden changes make the government an unreliable partner incapable of committing to anything beyond the next elections.
If the dominant ideology changes, it should only affect future grants, not current grants. Ideally, grants that have already been submitted or are close to submission should be evaluated according to the old rules. Otherwise a lot of time and effort will go to waste.
Europe is circling the drain, Taiwan is inconsequential and becoming less so by the day, and China does not respects it's citizens, they treat them like cattle. But okay sure, India's opinion is super important, especially as they are profiting off the Ukraine war.
I think it's pretty telling that you listed 3 countries you are absolutely not friendly with, and so whose opinion of America's reputation is not really relevant.
There is an Egyptian say that would translate to something like
"We didn’t see them when they were stealing, we saw them when they were fighting over what was stolen"
That describes this situation. Although to be honest all this aggressive scraping is noticeable but for people who understand that which is not majority of people. but now everyone knows.
> Although to be honest all this aggressive scraping is noticeable but for people who understand that which is not majority of people.
When you say noticeable, do you mean in like, traffic statistics? Or in what the model knows that it clearly shouldn't if it wasn't trained in legally dubious ways?
- Minimum "Biased" data
- "Discrimination" or "Discriminatory" variables
- Phase space "excluded"
- "Inclusion" of data/variable/anything
- "inequality" -> wow bell's inequality and all this theory work about inequalities will be triggered
These are just example that came into my mind from quick thought and skimming. I'm pretty sure that this will have much worst false positive rate. I would really be surprised if the vast majority if not all of projects get flagged. I'm also sure that 100% of statistics work or project heavily reliant on statistics (probably everything else too) will be flagged.
reply