Hacker Newsnew | past | comments | ask | show | jobs | submit | BudaDude's commentslogin

I was thinking a Warthog

https://www.halopedia.org/Warthog


Agree 100%

If you look at the past, whenever Google announces something major, OpenAI almost always releases something as well.

People forget realize that OpenAI was started to compete with Google on AI.


I love Cursor, but it feels like a ticking time bomb with extensions not being updated at the same rate as VSCode.

Also another issue I am starting to see is the lack of shared MCP servers. If I have VSCode, Cursor, and Claude open, each one is running its own instance of the MCP server. You can imagine that with a dozen or so MCP's, the memory footprint becomes quite large for no reason.


It’s more of a ticking time bomb because it relies so heavily on upstream model providers who all have competing products, particularly Claude Code.


I think about this daily. More devs are starting to pick up on Claude Code. The initial “not an IDE!” scare is usually diminished within the initial session.

I don’t think the future of agentic software development is in an IDE. Claude Code gives me power to orchestrate - the UX has nothing to do with terminal; it just turns out an agent that lives on the OS and in the filesystem is a powerful thing.

Anthropic can and will evolve Claude Code at a pace cursor cannot evolve IDE abstractions. And then yea - they are designing the perfect wrapper because they are also designing the model.

Long bet is Claude Code becomes more of an OS.


You might find this post interesting: https://steipete.me/posts/2025/claude-code-is-my-computer

It… sure is something. I’m still thinking about if it’s horrible, visionary, or both.


Note: the text of that article itself is AI generated.

> Automate Content: Like this very post. I use Wispr Flow to talk with Claude, explain the topic and tell it to read my past blog posts to write in my style.


Now I have the mental image of the owner of that blog tearing his hair out trying to get back into his computer, while the AI that locked him out is happily posting on his blog trying to convince other gullible humans to hand over control of their computers.


Yes, the author (apparently) spent a lot of time with it.


Wow yea, definitely resonates thanks for sharing.

This is why I think the future may be less about “agents” and more about “intelligent infrastructure”

I don’t want to chat. I want to point a wand and make things happen.


How are people using Claude Code day to day without spending a lot? I tried it on a moderately complex task and it chewed through tokens at an alarming rate. I quickly spent $2 and hadn’t even arrived at an adequate solution yet. I’ve heard other people say they’ve spent $10-20 in a coding session. I don’t see how that’s sustainable for me, so I’ve stuck with my $20/month Cursor subscription.


They use a plan - Pro and Max are static plans with different caps over 5 hour sessions.


Pro isn't a static plan. Pro subs can access Claude Code but are paying via API metering. I have it setup at home and, while I haven't used it much, it can quickly add up.

What I did do, because my personal projects aren't too complex, is moved the model from Opus to Sonnet which is about 1/5 the cost.

For day-to-day stuff I have ProxyAI (on IntelliJ, continue.dev works for this too) pointed at Mistral's Codestra for auto-complete and to Claude 4 for chat.

Claude Code is just for giving the bot tasks to do without me being deeply involved in the work.

(edit) I just saw that pro is getting a rate-limited option for Claude code for the sonnet model only. I haven't tried it out but will give it a go sometime. https://support.anthropic.com/en/articles/11145838-using-cla...


Pro is indeed a static CC plan as of yesterday. It won't automatically switch over, you have to re-login inside of Claude Code.


Normally to make a new smallish feature it costs me about $0.40.

The core suggestion is to point specifically at the files you want it to read and use as a reference, otherwise it might go read some huge file for no reason. Also the tokens used depend on the size of the project.

Generally, if I'm doing something I can box, I'd use chatgpt and copy it in myself. If I want something matching the style, I'd use a guided Roo Code.


Until Claude Code becomes manageable price wise, I don’t think Cursor really sees them as their competition. I can burn the whole cursor subscription price in a single day with Claude Code.


I've found Emacs plus gptel very pleasant to use. And following the ethos of Emacs, it is backend agnostic and very malleable.

Besides, if you want something inexpensive, using Gemini 2.0 Flash as a backend is completely free. Google provides an API key at no cost.


Ha, same. How do you use it? I tried all the fancy context management stuff multiple times, but I mostly just have a chat buffer open and copy paste stuff manually. Text wrangling is so damn efficient in Emacs. I pay around 10$ to Anthropic per month in API tokens for pretty heavy usage. With deliberate context management (I found keeping it small and focused vastly improves responses), cost is really not an issue.

Didn't try anything agentic within Emacs yet, don't find that helpful enough so far.


> tried all the fancy context management stuff multiple times, but I mostly just have a chat buffer open and copy paste stuff manually.

As of last week you can insert a link to a plain-text file in a chat buffer to include its contents in the prompt. It must be on a line by itself. In Markdown it looks

[like this](/path/to/file)

with Org links in Org chat buffers.

This feature is disabled by default to minimize confusion. To enable it you can flip the header line button that says "ignoring media" to "sending media". This works for sending images and other media too, if the model supports it.


Nice! I love how practical gptel is :D


> How do you use it?

I have a global bind for gptel-send (C-c g).

Then, in any buffer, I typically type C-u C-c g.

This lets me customize the prompt and lots of parameters, such as the context, before gptel-send is actually called.


I tried aidermacs yesterday, it's neat if you use the vterm backend. Does a few things more automatically.


I'm surprised nobody is mentioning how cheap copilot pro is. $20 and you get all you can eat inference without using your own api key for the models on vs code agent mode.


Copilot pales in comparison to Cursor Pro. I've trialed it three or four times in the last two years and stopped using it after a few days each time. Honestly, I have no idea why anyone pays for it given the alternatives.

My only wish is that Cursor had partnered with Zed. vscode isn't enjoyable.


FWIW,you can log in to github copilot with Zed and it will use your copilot subscription instead of needing to pay for api calls.


I'm sure it is but cursor plus API usage is out of reach for my hobbyist usage


I’m on Pro+ and get rate limited heavily. 1-2 hours of semi heavy use and the brakes kick in. I can’t stay productive in it because this always rips me out


All copilot models feel lobotomized. It’s like they’re deliberately running them at low performance or something.


I use with the Max plan ($100 per mo) and its well worth the money and only hit the limit once so far.


I’m now also on Max but had to upgrade to the 200 plan in about a week of daily rate limits

The $200 plan so far has been fine. Only had it once that it looked like I might hit the limit soon, but that was a very heavy refactoring task


Yeah, if you're a heavy user of Claude code, you pretty much need to use it with a Max subscription rather than a BYOK approach. But that starts at $100 / month so it's a significant bump from cursor.


> need to use it with a Max subscription rather than a BYOK

Why is that?


Max is far cheaper.


For any professional SWE 1/200 a month is basically nothing in terms of the value it delivers. They just rolled it out to the 20/month plan with limited usage but as soon as people get used to it I have no idea why they wouldn't upgrade unless they are just entering the field and don't have a job yet.


Anyone pulling that a month not working for themselves doesn't have to think about the cost. That kind of salary is paid by corps with strict privacy policies.

Unless you do nothing else with your time I'm not sure how you'd utilize the $100/mo plan fully.


the pricing is for token usage in 5/hr windows not monthly caps. if you use it intensely a couple times a month within a 5hr window it's not hard to hit the cap and want to upgrade. Personally I just work on some side projects during work on another monitor and just every half an hour so throw something at it and that's been very valuable for me.


225 messages every 5 hours? You hit that on the side while you're doing your day job? I suppose if you push all work to Claude and do nothing else all day it could be a concern but I don't think it would be a very effective way to work in it's current state unless you want to be left with a giant mess.

I admit their transparency around limits is a bit questionable. Why don't they just list out the tokens and remaining time?


Yeah I hit it again today, refactoring can use a ton. It did make a bit of a mess but planning it out making sure everything is tested and having it run through checking the tests making sure they all still pass uses lots of tokens but passively doing that while I'm working is way faster than doing it manually.

Sometimes I'll just experiment with weird stuff and end up reverting it or delete it afterword's. Also fun to build really nice data visualizations for data I'm working with.


> For any professional SWE 1/200 a month is basically nothing in terms of the value it delivers.

If it is delivering that value indeed, then 100-200 dollars each month is exactly what that professional SWE is worth.

That SWE is going to have to pivot into something adjacent to provide value-add, and if the only value-add is "I can review and approve/reject", then it's only a matter of time[1] that there are no SWEs who can review and then approve/reject.

And that is assuming that the LLM coding performance remains where it is now, and does not improve to the review, orchestration, design and planning levels.

-------------------------

[1] Due to attrition


They just announced Claude Code will come with the pro subscription ($20)


Interesting, but the limit is really low:

> Pro ($20/month): Average users can send approximately 45 messages with Claude every 5 hours, OR send approximately 10-40 prompts with Claude Code every 5 hours. [0]

I can probably run through that in 5 minutes.

[0] https://support.anthropic.com/en/articles/11145838-using-cla...


I’ve been running on this plan all morning (Australia time). Amazing value.


The $17 Claude pro sub has access to Claude Code now, at a fixed cost. Cursor also hits limits. I spent $350 on Cursor overage in like a week.


Claude Code now comes with the $20 Pro subscription plan.


And models eat apps over time. If you build an app that’s valuable, OpenAI takes note.


One of the first features we added to FastMCP 2.0 [1] was server composition and proxying (plus some niceties around trying to reuse servers whenever possible) for exactly this reason, so that you can ideally run a single instance of your preferred servers without replicating the setup over every application. In some ways, MCP standardized how agents talk to APIs but introduced a new frontier of lawless distribution! This is something that has to improve.

[1]: https://gofastmcp.com


I just run two IDEs.

Cursor is essentially only the wrapper for running agents. I still do my heavy lifting in Jetbrains products.

It actually works out well because I can let Cursor iterate on a task while I review/tweak code.


Have you tried the Jetbrains agent, I think it’s called Jennie? I am trying it right now and it seems decent enough but I haven’t tried Cursor as I don’t really like vs code.


I tried previous iterations of JetBrain's AI without much love, but need to look at Junie.

Using Windsurf plugins in JB ides has been working for me, albeit not as powerful yet as the Windsurf VS Code fork.


have you compared Windsurf (previously codeium, had to look it up) to Github Copilot agent or ChatGPT? I'm mostly still using ChatGPT's App integration. It can see my currently open files in webstorm and can directly suggest and apply changes from the app. And I find the suggestions better then JetBrain's AI integrations. But curious about Windsurf / CoPilot Agent


Jetbrains Junie is pretty good and comparable to Cursor in my experience. And since it is already included in my Jetbrains license, I have had no need for Cursor.


A bit.

Last time I tried, it didn't support RubyMine (whomp)


Same here, everyday coding in Webstorm, Oh I have a task I can offload to copilot, I open VSCode and let a Github CoPilot Agent do that.

Knowing what tools are better for what really helps.


have you tried the CoPilot agent tab in Github copilot chat in Webstorm? I wonder if/why you find using it through VSCode better in any way then using it directly in WebStorm.


I use the Claude Code plugin in PyCharm in the same way.


That's why i use Docker MCP Catalog. One MCP Server to rule them all. more info: https://www.youtube.com/watch?v=6I2L4U7Xq6g


Here’s an alternate link if you prefer to read text instead of watching a 6 minute video: https://docs.docker.com/ai/mcp-catalog-and-toolkit/catalog/


I wrote my own tool for that too :D

https://github.com/tuananh/hyper-mcp

it's a MCP server with WASM plugin system, packaged, signed & published via OCI registry.


I recently discovered toolhive which is pretty handy too https://github.com/stacklok/toolhive


I don't understand. Is this meant to run locally? Because I tried to deploy my agent using GitHub MCP server to K8s. I can't ask my agent to run docker command in a pod.


Cursor and other VSCode forks connect to Open VSX [1] for extensions. Barring some of the Microsoft extensions, I've found that pretty much all the extensions I use are available and kept up to date on Open VSX. Cursor seems to have enough funding to support their own variants of the Microsoft extensions, like Python and C++.

The one issue I've run into is that the VSCode version Cursor uses is several months old, so we're stuck using older extensions until they update.

[1] https://open-vsx.org/


You can change it back to use the normal Microsoft marketplace


How?


Add a `product.json` and set the extension gallery URL through that

``` { "extensionsGallery": { "serviceUrl": "https://marketplace.visualstudio.com/_apis/public/gallery", "itemUrl": "https://marketplace.visualstudio.com/items", "cacheUrl": "https://vscode.blob.core.windows.net/gallery/index", } } ```

https://github.com/getcursor/cursor/issues/2195

This is technically against the ToS of the extension gallery though


> If I have VSCode, Cursor, and Claude open

This is good user feedback. If Cursor is "Claude + VSCode", why do you need the other 2 open?


for me, I’ll keep doing work on the codebase in a separate vscode while Cursor’s agent is wiling away at it, so as to not be distracted or interrupted by the agent activity in the corner of my screen. and then i’ll have a claude or aistudio tab open doing bigger analysis or planning tasks, reading papers together, etc.


What would you say to somebody who doesn't trust Cursor to "take the reigns off" and go "agent mode" and do such large changes? Even with "checking/approving/having the final say" as a user, I feel there is time lost if the AI does not do the changes the right way/makes small pesky mistakes.

Autocomplete: yes

Asking questions: yes

I know everybody is all into agent mode and it isn't a Cursor specific thing, I'm just confused why everybody is into it.


I just accept that when I return to the Cursor window, it is going to have made some mistakes and I’m going to have to spend some time fixing things. I agree it’s a delicate balance, and sometimes it feels more like I’m exploring methods of steering the AI than I am doing anything about the code.

my usecases have been building relatively self-contained, well-specified components of distributed systems out of academic papers and my own design notes / prototype skeletons, in rust. there’s a lot of context for the agent to ground against, and it can blow out ideas into their implications relatively well ime.

the experience of fixing up lots of pesky mistakes that you yourself would never make is kinda annoying.


Just use other transport like streamable http.

i wrote a MCP with plugin system where you only need to run 1 instance and add plugins via config file.

https://github.com/tuananh/hyper-mcp


What are you using MCP for?

We recently launched Zapier MCP, we host the servers for you: https://zapier.com/mcp


why would you open 3 IDEs all at once :-)


TIL that it doesn't have the same extensions as VSCode. I thought they share the same directory.


This is only effectively a problem for a handful of MS vendored extensions.


Just run it on http


this is the way.

STDIO MCP is really just a quick hack.


They are also for the most part avoidable


I would agree with you if this was a main line product (iPad, Macs, iPhone). You could argue the Apple Watch is a main line product as well.

But this is an accessory line. Apple is pretty good at keeping accessories working for as long as possible. AirPods v1 still work. A Magic Mouse bought 10 years ago still works as long as the battery isn't dead.


actually ... it doesn't. Well, you can't use them with a phone anymore because they did exactly as described. The new mice work fine though.


I truly wonder can be done at this point if congress already passed it into law and judges have sided with congress.

At the minimum it would be nice if some actual concrete evidence came out to why it was banned. Not just more "It's a Chinese spying app that knows you like watching brainrot and its bad"


If the first amendment goes, so does the rest of the amendments and probably the constitution with it.

This isn't the America of 1776. We have turned from a handful of somewhat consolidated groups that could be treated with a broad brush into 360 million screaming individuals with no leader and no cohesive American dream for the next 30 years to shoot for.

I don't use tiktok, I don't care for it.

But I don't think that congress should have the right to take away their ability to operate, only that they should have the ability to not allow exfiltration of American PII to other nations.


Whelp, this is a bi-partisan congress who voted for it, the House representative and Senator you voted for probably supported this act too. And it's not a narrow majority, it's an overwhelming one. And the courts fully support it to.

When you were voting for your representative, would it not have been probable to know they likely would have supported the act? This bill and backlash has been building for years. It's unambiguously clear that America has made her choice here. There is no risk of "authoritarianism" because the overwhelming political plurality is in consensus. Nor is there any concrete political opposition or protests.

Thankfully, the internet isn't real life, and I'm hard pressed to know of the majority complaining here really are Americans with the best interests of America at heart or if they're mad because the interests of a certain country gets harmed here.


> There is no risk of "authoritarianism" because the overwhelming political plurality is in consensus. Nor is there any concrete political opposition or protests.

You could write three books on those two sentences


Repubs put it in with Ukraine aid to force it through.

And a consensus doesn’t mean it isn’t against the principle of the country and the first amendment. Literally. Banning. Speech.


>Repubs put it in with Ukraine aid to force it through.

The bill passed with the House with 352-65, which I recall this forum often says is more representative of the population than the Senate. You're implying that Republicans bundled it against the opinions of the Democrats when it reality it was more of matter of expendiency for a bipartisan addition with the foreign aid bill. Biden obviously signed it off, the Democrats overwhelmingly support this bill, it's the Republicans who care more about free speech anyways.

>And a consensus doesn’t mean it isn’t against the principle of the country and the first amendment. Literally. Banning. Speech.

That's just your individual interpretation that the divestment bill conflicts with the "principles" and the first amendment, clearly the house, the senate, the courts do not. America dosen't share your opinion on that matter. A more obvious principle of American Principles is respecting the democratic process even if you don't personally agree with the conclusion.


No he couldn’t have not signed it because that would mean aid was not passed. I literally spelled it out for you.

America and any citizen can want a dictatorship. That doesn’t mean it was part of the founding principles. That’s a logical fallacy you’re making.


>No he couldn’t have not signed it because that would mean aid was not passed.

Biden literally said if they passed it in the House, he would sign it. You're trying to insinuate that this is not what the Democrats or Biden wanted when all indications of their statements and actions show the exact opposite.

>America and any citizen can want a dictatorship. That doesn’t mean it was part of the founding principles. That’s a logical fallacy you’re making.

No, the logical fallacy you are making is that you are placing your interpretation that this is a violation of the first amendment as an objective fact, when it's just an opinion that the House, Senate, Courts and the Presidents disagree with you on.


No, I am arguing just against your point that something can’t be against the first amendment/constitution etc just because the majority of Americans are for it.


TikTok said it wasn't exfiltrating data and turned out to be lying.

I don't really understand the argument that this is a First Amendment issue. TikTok was asked to protect its users from CCP surveillance. It didn't. Now the US is forcing it to cut ties with the CCP.

TikTok can continue to operate if it complies. Its owners and users have lost no freedom to speak either way.


> TikTok said it wasn't exfiltrating data and turned out to be lying.

Is there a source for that?

The Wikipedia article [0] states "There has been no public evidence of American TikTok user data being accessed by the Chinese government" backed by three sources (124-126) from earlier this year.

[0] https://en.wikipedia.org/wiki/Restrictions_on_TikTok_in_the_...


https://www.forbes.com/sites/antoniopequenoiv/2024/05/06/for...

> A former TikTok executive suing the platform alleged Monday that ByteDance, TikTok’s China-based parent company, has far more extensive control over the social media platform than it has claimed


The argument against TikTok has little to do with PII.


> All tablets are dying.

Highly disagree. The iPad line is very strong, especially in the artist community.


A beefier Switch is what everyone wants. The number 1 complaint I hear about it is how game X looks worse on it than the Xbox/PS version.

Hopefully Nintendo learned its lessons from the Wii U.


A beefier iteration is the Xbox PlayStation way. To many people what makes Nintendo special is that they often avoid that. Wii, Switch, snd DS being successful examples.

>Hopefully Nintendo learned its lessons from the Wii U.

That’s my concern, Nintendo doesn’t like incremental titles like “Switch 2”. They’d rather call it something weird like “Switch Me” which only confuses non informed customers.


If they were on their game it would just be "Big Switch".


The only thing I want is to be able to play totk without horrific fps drops. That’s all


> Hopefully Nintendo learned its lessons from the Wii U

But... this is in direct contradiction to what you're saying.

The Wii U was essentially a beefier Wii and it failed. It wasn't revolutionary, wasn't much of a new form factor. But it did have beautiful games.

If you look at all the Nintendo consoles that ate up the competition, none of them are "iterations". They're brand-new things. DS, Wii, Switch were all major departures from what came before them.


Agreed, a lot of people were expecting a bump in processing power in the OLED refresh, but it's pretty clear now that they were saving that for the Switch 2.


Yeah playing emulated Switch games is a much better experience on a Steam Deck than it is on the Switch. Nintendo is in a weird spot now because the competitive landscape is much different.


You are forgetting the handheld line

Gameboy Color supported OG Gameboy games

GBA supported GBC games

DS supported GBA and(?) GBC games - Could be wrong about that

3DS supported DS games.


DS did not support GBC games.


The GBA (original and SP) also supported OG Gameboy games, but the Gameboy Micro only supported GBA games

The 3DS also had games from other consoles for sale in the eShop, but they were emulated (GB, GBC, Game Gear, NES, SNES). If you bought a 3DS before the price drop, you could also play some GBA games. These are also running natively, not emulation https://en-americas-support.nintendo.com/app/answers/detail/...


Game Boy Micro can still enter GBC mode, it just can't read any cartridges. It's missing the switch which is normally triggered by the cartridge shape, and also missing the voltage conversion circuitry.


Tinder isn't exactly innocent in this.

Tinder isn't making money on people who match with people successfully and never come back to the app. The managers tweaking the algorithm know this.


Dating apps are hard to make profitable.

Your most successful customer is the one that no longer needs your platform, so a monthly fee or relying on ads does not work. You end up with a perverse incentive to make sure users only ever get "okay" matches, and never GOOD or even GREAT matches.

But if you charge a one-time fee, then the barrier of entry is too high and you won't get many people buying, especially once the people who are frankly undateable start bad-mouthing your app.

You could try a method where you only pay once you decide you landed a good match, but that's going to be impossible to enforce without greatly giving up privacy.


Still could be way less hostile than what Tinder is right now.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: