> It would be a huge step up if agent could interact with LSP (Language Server Protocol).
>
> It would offer :
>
> renaming all instances of a symbol over all files in one action
> quick navigation through code : fast find of all references to a property or method
> organize imports, format code, etc…
And last Friday a Cursor engineer replied "Thanks for the idea!"
So how does the AI agent in Cursor currently have access to LSP?
(I am most interested in having the agent use LSP for type checking, documentation of a method call, etc. rather than running slower commands)
(note, there is an open PR for Zed to pull LSP diagnostics into an AI agent thread https://github.com/zed-industries/zed/pull/42270 but it would be better if agents could make arbitrary LSP queries or something like that)
It would be so cool if LLMs could get the type of a variable when it's unclear (specially in languages with overloading and whatnot). Or could get autocomplete if they get stuck with a code. Really I think that agents and LSP should be hybrid, and maybe the agent could inform the LSP server of some things like things to warn (IDE diagnostics could be driven by a combination of LSP and AI agents)
“firing people while turning a profit is 100% bad faith that should be regulated or barred.”
That’s far too broad a claim. Just because you’re turning a profit doesn’t mean you should be locked into keeping all of your employees. Some are likely to be underperformers who don’t bring sufficient ROI compared to other investments/hires you could make.
My experience with these sorts of layoffs is that they are not tightly bound to performance. If you have underperformers you can fire them the ordinary way.
Exactly. How is it that an org suddenly discovered thousands of employees are under performers? And how is it that the number of under performers coincides with the number McKinsey and Co (or similar company) said it would be?
>Exactly. How is it that an org suddenly discovered thousands of employees are under performers?
The more correct statement is they suddenly cared about under performers. It's not any different than say, you noticing your grocery bills going up and as a result you cancel all the subscriptions you don't need. It's not like all those SaaS services' value propositions suddenly plummeted because the price of eggs went up, but now you suddenly have an eye for cutting costs.
At this point I would not be surprised if there isn't an "AI" tool that looks across employees by salary range, department earnings, seniority and age and just generates a list at a moments notice.
I was around for a desperate layoff at a small company in the early 2ks and got to watch as management basically ran around the office doing this logic in real time. Some people are get pulled in because they aren't high performing or they're unliked, but most was a simple expense/income calculation.
Literally this. Corporations are good at making up plausible excuses, but anyone who takes more than two seconds to evaluate their claims beyond face value will find they’re almost always complete bullshit.
Underperformers should be rotated out long before a mass layoff occurs. If your company isn’t axing them until a mass layoff, they’re doing bad business.
This, plus companies do different stuff. If eg. amazons streaming service fails, but normal sales of physical items surge and in total, compensate to make a profit, you can't really move streaming developers, marketers etc. to warehouse jobs.
> If it really was "just a complex situation", you would expect equal percentages of simple and complicated cases for regular joes and huge corporations, no?
Obviously not. Regular joes almost always have relatively simple situations relative to multinational corporations, otherwise they wouldn't be regular joes.
Can you explain the obviousness? Other than a lot of money being involved, what makes it "obvious" that the way corporations break the rules is more complex than the way natural persons break the rules?
What makes it obvious or inherent that a corporation breaks the law at some edge case of the law that requires a lot of time and detail and multiple lawyers to figure out, and not so for a random guy? I think you are confusing money with complexity.
I don't see how a person modifying their car in their garage is a more complex way of breaking the law than WV making cars so they cheat emissions tests. This is not about the complexity of engineering, or the complexity of logistics. Those things do not matter. What matters is whether the law was broken or not, and what the just penalty is. It is not at all obvious to me the way VW did it is more complex. You just claim it without any supporting evidence or argument.
Still relevant, as it means that a coding agent is more likely to get things right without searching. That saves time, money, and improves accuracy of results.
Citation needed for the idea that zero is the optimal price for public benefit. Among other issues, I expect medication compliance would be higher when the patient has to pay for the medication.
I think we probably have data on that (at least in general). That is assuming people react to out-of-pocket payments, and not to how much their insurance or the NHS etc is paying.
I’m not a celebrity or superstar, and I’ve successfully used his techniques several times. The very first time it resulted in $20k improvement over the initial salary offer. Another time it resulted in an additional $40k in signing bonus.
Most recently it resulted in a modest $5k boost to the offered salary.
But the level of success you are likely to experience entirely depends on the alternatives that you have and the alternatives they have.
(I should also note that I’ve never been located anywhere like SF.)
