I've found that having the coding assistant do large tasks like this unsupervised is the worst way to use it. Asking the assistant to do narrowly defined tasks and then checking the work is the only reliable way.
I've been working with Cursor for a few months. I learned quickly to stay away from the hype around creating entire features using Composer. Found a ton of value in using it to work with context from the codebase as well as external documentation.
Acquired had a great episode earlier this year that really connects with this. They talked about how Novo Nordisk stuck with GLP-1 research for decades, even when it didn’t seem like a sure thing.
A big part of that was Mads Krogsgaard Thomsen, who pushed for GLP-1 research at Novo even when he faced a lot of skepticism and wasn't always treated well for it. Compare that with MetaBio—mentioned in the study—where Pfizer pulled the plug early and missed the boat entirely. Novo’s persistence, especially Thomsen's, led to Ozempic and Wegovy
So much of this is hindsight bias though. There were no shortage of people with ideas and companies pursuing obesity drugs through a number of different pathways. Only in hindsight does it seem "genius" that Thomsen persisted and succeeded where nobody else did. But there are dozens, hundreds, of other smart people who were pursuing other pathways who did just as much stubborn work but didn't get a result. That's just pharmaceuticals.
Take, for example, another high profile disease - Alzheimer's. First there was the beta amyloid theory, then there was the p. gingivalis theory (this one was talked about so highly on this very forum, but ended in an equally high profile failure* of a pivotal clinical trial by Cortexyme). Now there are viral and metabolic theories. Each of these theories have a few dozen companies and armies of PhDs stubbornly pursuing a miracle drug, but so far it remains elusive.
* We also like to talk about "failures" of clinical trials, which is technically correct language, but evokes in the public imagination the wrong idea. A clinical trial failure doesn't mean there was something wrong with the idea or process (long before it ever gets there, a drug candidate would have been proven to be very effective in lab tests and animals). It's just that 90% of clinical trials don't end up working due to complex disease pathways and numerous unknown factors. It would help if we talked about "negative proofs" (i.e. proving something doesn't work is also valid), but it's not quite as catchy.
First? Isn't the beta-amyloid cabal still blocking all Alzheimer's research unless the researchers find a way to even tangentially support that long disproven theory?
Karen Ashe and Sylvain Lesné at Minnesota published a fake paper that redirected billions of research into the trash bin. https://www.science.org/content/blog-post/faked-beta-amyloid... Amazingly both still have their jobs for life, both still publish, Ashe is still a member of the National Academy of Medicine, both are still getting grants.
This is a mischaracterization of the scope of the fraud. Lesné clearly committed fraud, but his work was not foundational. The fraud did not "redirect billions".
Yes it very much did lead to billions of wasted dollars and that's if you count us public funding alone. Tens of billions of you count non us and private funding.
The Nature paper has been cited in about 2300 scholarly articles—more than all but four other Alzheimer’s basic research reports published since 2006, according to the Web of Science database. Since then, annual NIH support for studies labeled “amyloid, oligomer, and Alzheimer’s” has risen from near zero to $287 million in 2021. Lesné and Ashe helped spark that explosion, experts say.
The paper provided an “important boost” to the amyloid and toxic oligomer hypotheses when they faced rising doubts, Südhof says. “Proponents loved it, because it seemed to be an independent validation of what they have been proposing for a long time.”
From your description, it sounds like a large complex ecosystem (of which Lesne and Ashe were important parts) redirected billions. I think it’s a bit overselling it to say that their results alone redirected billions
As unavoidable mentioned, there are viral theories.
In Science, from July, "Can infections cause Alzheimer’s? A small community of researchers is determined to find out. Following up tantalizing links between pathogens and brain disease, new projects search for causal evidence", https://www.science.org/content/article/can-infections-cause...
I mean, that's the point - in pharmaceutical sciences there's _so much noise_ including fraud that it's really only easy in hindsight to pick out "the guy" who was the "genius". It's hard to take one story like this and make it a repeatable success.
> So much of this is hindsight bias though. There were no shortage of people with ideas and companies pursuing obesity drugs through a number of different pathways. Only in hindsight does it seem "genius" that Thomsen persisted and succeeded where nobody else did. But there are dozens, hundreds, of other smart people who were pursuing other pathways who did just as much stubborn work but didn't get a result. That's just pharmaceuticals.
Exactly.
There are plenty of examples where the opposite choice was made - argue for continued development despite high uncertainty.
The CETP inhibitors is a good one. Pfizer flushed several billion dollars down the drain with the decision to push it through phase 3.
^^ Here's an article written by Lotte Knudsen, referenced in the original post, that further tells the story of how GLP-1 was first developed into a drug (as liraglutide) and approved for human use. There were a lot of false starts and additional practical problems that needed to be solved in order to yield a viable medication.
After reading the OP I was surprised to learn that Novo Nordisk picked up the research only a couple of years after GLP-1 was abandoned by Pfizer, after which it took 5 years to develop the initial medication and another 12 years to make it through FDA approval. Even after all that, the primary indication was for diabetes. It took another 7 years for semaglutide to make it through approvals and bring GLP-1 into the public consciousness.
When you consider the amount of time involved, and the sustained investment required, it's difficult to fault the execs at Pfizer for their decision to shut the project down. Obesity wasn't nearly as prevalent then as it is now, and it seems likely they had funded the startup specifically because of the author's prior research into nasally-administered meds. It's even possible that the shutdown decision had little to do with the primary area of research.
It is an expected behavior. context is missing. if you know any websites that has your request then you may mention it in your query with context. so that you can force the agent to look the info you need.
for e.g
any available 3 bedroom units currently for rent in Seattle
use these resources: Zillow, redfin, realtors.
Great episode of the Lawfare podcast recently where Shane Harris interviewed Benjamin Breen about his book, Tripping on Utopia, which tells the story of how Mead’s research into expanded consciousness and psychedelics.
we started using (and now contributing to) https://orval.dev/ this year which both generates the mocks using MSW as well as the client-side networking code (React Query in our case). It removes so much boilerplate its amazing.
Orval is great, I also recently wrapped up a project with Orval, React Query, and MSW. Generated my typescript models, helped me track changes in the API each time I updated against the swagger spec and let me test and demo the UI before our API team had a server running. Such a time-saver.
dataPlor is looking to hire a senior Ruby engineer to help us expand and grow our international data product (POI, geolocation, spatial econometrics).
Requirements
Ruby on Rails
SQL, PostgreSQL
Rspec
Bonuses
JavaScript
React
AWS/Azure
AI Chat bots
Compensation
Competitive salary
Annual Bonus
About dataPlor
dataPlor is an early stage, venture backed startup that provides the only accurate database of small business information in LATAM. Our customers include American Express, Google, Uber Eats, and iFood.
I've been using Cursor since the summer and wrote up a few tips here https://betaacid.co/blog/cursor-dethrones-copilot