Hacker News Reader

Comment by nojs | Hacker News Reader

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.

View on HN

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.

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.

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.

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.

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.

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

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

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.

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.

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.

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

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'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.

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

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.

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

Reply on news.ycombinator.com