A flat pricing subscription for Claude Code • Hacker News Board

Re: A flat pricing subscription for Claude Code

#281

Post by vidarh » Sat, May 10, 2025, 12:14 PM UTC

UncleEntity wrote: post #195

vidarh wrote: post #155

Earlier quoted context omitted.

A couple of tips if you're just starting with it: The two worst ways of burning API credits I've found with Claude Code are: 1. Getting argumentative/frustrated with the model if it goes off the rails and continuing to try to make something work when the model isn't getting anywhere. If it really isn't getting something in the first few prompts, stop and rethink. Can you go back and set a smaller task? Like writing t…

> If it really isn't getting something in the first few prompts, stop and rethink. Can you go back and set a smaller task? Like writing test cases that it's broken approach would fail? This. I was fighting with Claude for a good chunk of yesterday (usage limits seemed broken so it didn't really time me out) and most of that was getting it to fix one small issue with three test cases. It would fix one test and break t…

> Now I just assume Claude is being intentionally daft and treat it as such with questions like "why would I possibly want a fix specifically designed to pass one test instead of a general fix for all the cases?" Oh, yeah, that's its new trick, rewriting the code to only pass the failing test and throwing everything else out because, why not?

The best one I've seen is when it tries to disable a test because it can't make the code pass it.

You do need to treat it as if it's trying to sneak stuff past you sometimes because you do get the occasional bout of what in a human I'd have treated as "malicious compliance", at a level well beyond stupidity.

Re: A flat pricing subscription for Claude Code

#282

Post by player1234 » Sat, May 10, 2025, 2:08 PM UTC

phyalow wrote: post #206

blitzar wrote: post #204

Earlier quoted context omitted.

LLMs are a solution in search of a problem. The first problem they have gained traction on is programming auto complete, and it is useful. Generating summaries, pretty marginal benefit (personally I find it useless). Writing emails, quicker just to type "FYI" and press send than instruct the ai. More problems that needed solving will emerge, but it will take time.

Deep research has saved me weeks worth of man hours in the last couple of months…

How did you measure this?

Re: A flat pricing subscription for Claude Code

#283

Post by LtWorf » Sat, May 10, 2025, 10:03 PM UTC

pc86 wrote: post #215

guappa wrote: post #171

Earlier quoted context omitted.

Ah yes, LLM is very good at giving me information from documentation that was out of date 15 years ago instead of using the documentation from 2025.

Most LLMs, especially the paid tiers, will fetch updated information. This was a valid complaint perhaps 8-12 months ago.

You mean they will DOS the servers of the open source projects? That's even worse!

Re: A flat pricing subscription for Claude Code

#284

Post by auggierose » Sun, May 11, 2025, 6:50 AM UTC

dham wrote: post #275

auggierose wrote: post #140

Earlier quoted context omitted.

But at least Claude Desktop runs on my Intel Mac.

I'm sorry - Apple

It's more like:

    I'm sorry

    - Open AI

Re: A flat pricing subscription for Claude Code

#285

Post by Loic » Mon, May 12, 2025, 5:40 AM UTC

kridsdale1 wrote: post #251

asaddhamani wrote: post #148

Earlier quoted context omitted.

Nope, it can be even a dozen (because agentic). Claude usage limits are actually based on token usage, and Claude Code uses a mix of Haiku and Sonnet. So your limits are split among those two models. I gave an estimation of how much usage you can expect in another comment on this thread, but you will find it hard to max out the $100 plan unless you are using it very, very extensively.

I didn’t realize they were tuning cost optimization by switching models contextually. That’s very clever. I bet the whole industry of consumer LLM apps moves that way.

I am using cline, it plans with Haiku and execute with Sonnet. It works well.

Re: A flat pricing subscription for Claude Code

#286

Post by asymmetric » Mon, May 12, 2025, 12:57 PM UTC

saralily wrote: post #267

asymmetric wrote: post #241

Has anyone tried Claude Code with Vertex/Bedrock instead? How does it compare in terms of pricing?

Isn't it exactly the same on Bedrock as in the API?

Yeah you're right, the price is exactly the same, it seems.

Re: A flat pricing subscription for Claude Code

#287

Post by otabdeveloper4 » Mon, May 12, 2025, 2:55 PM UTC

firtoz wrote: post #151

otabdeveloper4 wrote: post #143

Earlier quoted context omitted.

LLM's don't increase programmer productivity. In fact, they actively harm it. Programmers aren't paid for coding, they're paid for following a formal spec in a particular problem domain. (Something that LLM's can't do at all.) Improving coding speed is a red herring and a scam.

It's very marmite. I used to hate it when it was vscode's crappy copilot. Now with Cursor and Windsurf, after some onboarding, I find it indispensable. I have used AI for coding for 3 separate roles: - freelancer - CTO - employee And in all 3 cases, AI has increased my productivity, and I could ship things even when I'm really sleepy or if I have very little time between things, I can send a prompt to an agent and th…

> TLDR: Skill issue

What's the skill set here? Spending four hours to massage prompts to painstakingly do what can be done manually in 15 minutes?

Re: A flat pricing subscription for Claude Code

#288

Post by Implicated » Mon, May 12, 2025, 9:17 PM UTC

oblio wrote: post #272

ajsisbdjxbx wrote: post #244

Earlier quoted context omitted.

How do you know what it built is correct if you don’t know C?

They'll find out by the CVEs 1 year later.

Aye, being that I have no idea what I'm doing I certainly won't be generating a PR of this code and am willing to take the risk of there being an issue from my adding (rather straightforwardly) a handful of commands to an already existing and stable extension.

Re: A flat pricing subscription for Claude Code

#289

Post by otabdeveloper4 » Tue, May 13, 2025, 9:10 AM UTC

criddell wrote: post #174

otabdeveloper4 wrote: post #161

Earlier quoted context omitted.

You don't understand. The fact that getting a formal spec is impossible is precisely why you need to hire a developer with a big salary and generous benefits. The formal spec lives only in the developer's head. It's the only way. Does an LLM coding agent provide any value here? Hardly. It's just an excuse for the developer to waste time futzing around "coding" when what they're really paid to do is cram that ineffabl…

> The formal spec lives only in the developer's head. You and I have different ideas of what a formal spec is.

Programming language code is a kind of formal spec.

Re: A flat pricing subscription for Claude Code

#290

Post by firtoz » Wed, May 14, 2025, 6:52 AM UTC

otabdeveloper4 wrote: post #287

firtoz wrote: post #151

Earlier quoted context omitted.

It's very marmite. I used to hate it when it was vscode's crappy copilot. Now with Cursor and Windsurf, after some onboarding, I find it indispensable. I have used AI for coding for 3 separate roles: - freelancer - CTO - employee And in all 3 cases, AI has increased my productivity, and I could ship things even when I'm really sleepy or if I have very little time between things, I can send a prompt to an agent and th…

> TLDR: Skill issue What's the skill set here? Spending four hours to massage prompts to painstakingly do what can be done manually in 15 minutes?

No, it's more like knowing the strengths and weaknesses, and if the work is good, accepting, and if not good, directing in the right way. The latter may take some time to learn, for sure, but not that much, and once you know, it's faster and faster.