Hey! I really see the power in Zed and the extensibility and simplicity. Great approach.
I posted this above, but want you to see it:
Two areas where I think Zed might fall behind: Cursor Tab is REALLY good and probably requires some finetuning/ML chops and some boutique training data.
For composer, there's going to be more use of "shadow workspace" https://www.cursor.com/blog/shadow-workspace to create an agentic feedback loop/ objective function for codegen, along with an ability to navigate the language server and look up definitions and just generally have full context like an engineer
Also, cursor has a model agnostic apply model, whereas you all are leaning on claude.
Any plans to address this from the core team or more of a community thing? I think some of this might be a heavy lift
I really like the shared context idea, and the transparency and building primitives for an ecosystem
Thanks, I'll take a look at these. We aren't done–A good amount of the Zed team uses our assistant heavily every day so we'll continue to refine it.
I shared this with the team. I need to spend some time in Cursor to understand their mental model, it seems a lot of folks have come to enjoy using it.
We do also have extensibility planned for the assistant, you can see a taste of it in the slash command code if you want to check it out.
AFAIK you can use `/workflow` with some other models other than Claude, but I can't speak to which off the top of my head.
Two areas where I think Zed might fall behind: Cursor Tab is REALLY good and probably requires some finetuning/ML chops and some boutique training data.
For composer, there's going to be more use of "shadow workspace" https://www.cursor.com/blog/shadow-workspace to create an agentic feedback loop/ objective function for codegen along with an ability to navigate the language server and look up definitions and just generally have full context like an engineer. Are there plans for the same in zed?
Also, cursor has a model agnostic apply model, whereas you all are leaning on claude.
I think Zed is starting with a more transparent elegant foundations and then they'll build in more optional magic from there. For example, they're working on automatic codebase RAG
Why have residency spots shrunk per capita? Why do unmatched grads have to work at mcdonalds but NP's and PA's can practice with more latitude than some residents?
ACR for radiology is going on in Washington DC. Current staffing throughout the country is poor - over utilization of imaging and not enough radiologists. So we are lobbying for an increase in Medicare funding for residency positions (they are paid by Medicare). Also trying to get more J1 visas but that’s kind of dubious as we are taking physicians from another country who likely also needs physicians.
I have no idea why unmatched graduates are working at McDonald’s as you say. There’s always primary care positions open for the scramble last I checked. If they can’t get a spot there’s likely a real issue in their education or themselves. It’s a normal distribution of a population, MD or not.
I can’t speak to what NP and PA’s do - they have their own PACs and organizations. I know they want to increase their scope of practice and keep their liability low.
You can't legally practice as a primary care physician without one year of internship, after which you get unrestricted licensed. If you're unmatched, no internship. Is that not correct?
Yea that’s right. You can scramble separately into 1 year internships. Those are really easy to get - but the unfilled spots are not in happy places. They’re usually more rural and surgical.
But like you said if you have a year under your belt you can work in an urgent care or the like.
You think you’ll be able to recruit more people into medicine by reducing compensation, keeping education costs the same, and also keeping medicolegal liability on the physician?
Residency as “profit” is a stretch. You tread water for 5 years. If you would like those apprenticeship years to go unpaid then I’m not sure how it increases the number of people who want to go into medicine.
>You think you’ll be able to recruit more people into medicine by reducing compensation
You don't need to recruit more, there is an abundant supply of people who want it.
>Residency as “profit” is a stretch.
Physicians are funny, a fantastic wage for the lower-middle class is considered 'treading water'. And its for education. Something every other degree pays for.
>I’m not sure how it increases the number of people who want to go into medicine.
This is not an issue, there are plenty of people who want degrees that don't involve math. The issue is number of licenses, not number of people who are capable of doing the job and want to.
Residents should absolutely be paid. Years of often times reaching 80 hours/week, treating patients, performing procedures, writing notes - all is valuable labor.
It is like saying we won't pay you for the first several years of your first dev job because it is primarily a ramp up / educational period.
The labor isnt valuable thus cannot be billed and needs to be taken via taxes. It also means that whatever people are doing in residency, they don't need residency for. Licensure bullshit.
The labor is valuable and doesnt need to be taken via taxes.
Sorry. I have a brilliant, extremely driven friend who did undergrad at an ivy. After getting covid, She had to drop out of her grad school program and her new life is a shell compared to what it used to be like. 2 years later, and there's a tiny fraction of improvement which she attributes to extreme rest. I forward her literature about emerging LC treatments and mechanisms of which her physicians are laughably ignorant.
From what I read, for both Covid and Influenza, a certain percentage have lingering symptoms, but you cant say they are similar because some symptoms are much more life altering that others. A nagging cough is not the same as brain fog, for example. The life altering symptoms "seem" to be much worse with Covid.
