Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Claude Code SDK

docs.anthropic.com

Post reply on HN
Print view View original

111–120 of 201 posts

Re: Claude Code SDK

#111

Post by throwa27482 »

usrnm wrote: post #66
csto12 wrote: post #60

Earlier quoted context omitted.

If that’s the future, that means a massive reduction in software engineers no? What you are describing would require one technical product manager, not a team of software engineers.

> that means a massive reduction in software engineers That's exactly what everyone is hoping for. Well, everyone except software engineers, of course

Define everyone. I know a lot of SWEs who don't take their job for granted, always strive to add value, and try to keep skilled constantly and try to be extremely helpful. Maybe in SV where the salaries are high there is some schadenfreude but I don't see that on general for what is a worldwide industry. In most places it's just a standard job.

I don't understand the pleasure of putting people out of work and the pain on people's lives and careers but I guess that's just me.

Re: Claude Code SDK

#112

Post by m3kw9 »

When you have model lock in, it’s a big detriment to use because if anyone comes out with SOTA models, and you have already invested infra development on this, you are stuck. Even if you open it up, it’s likely not to work as your model is likely trained specifically on that CLI. Just look at Codex CLI, you can use Gemini 2.5 pro, but it will get randomly stuck or fail a lot vs OpenAI models

Re: Claude Code SDK

#113

Post by adefa »

buzzerbetrayed wrote: post #50
d_watt wrote: post #9

Earlier quoted context omitted.

Claude max plan has Claude code bundled into the price. $100/month isn't cheap, but the RoI is there for me personally.

Can you clarify what you mean here? Are you saying I can use Claude Code for a flat rate of $100/month? What are the limits? What if I use more than $100 worth of Code in a month? Their website doesn't seem to make it clear. Edit: Found the answer to my own questions > Send approximately 50-200 prompts with Claude Code every 5 hours[1] Damn. That's a really good deal [1] https://support.anthropic.com/en/articles/1114…

I have been using Claude Code a lot since the Max plan change and I've never hit the limits myself.

Re: Claude Code SDK

#114

Post by crazylogger »

ryandrake wrote: post #104
pjmlp wrote: post #72

Earlier quoted context omitted.

The moment I am able to outsource work for Jira tickets to a level that AI actually delivers a reasonable pull request, many corporate managers will seriously wonder why keep the offshoring team around.

It seems like the Holy Grail here has become: "A business is one person, the CEO, sitting at his desk doing deals and directing virtual and physical agents to do accounting, run factories, manage R&D, run marketing campaigns, everything." That's it. A single CEO, (maybe) a lawyer, and a big AI/robotics bill = every business. No pesky employees to pay. That's the ultimate end game here, that's what these guys want. Is…

Surely at that point the CEO would be AI as well.

The owner (human) would say "build a company, make me a billion dollars" and that would be the only valuable input needed from him/her. Everything else would be derived & executed by the AI swarm, while owner plays video games (or generally enjoy the product of other people's AI-labor) 100% of the time.

I'd argue GPT4 (2022) was already AGI. It could output anything you (or Tim Cook, or any other smart guy) could possibly output given the relevant context. The reason it doesn't right now is we are not passing in all your life's context. If we achieve this, a human CEO has no edge over an AI CEO.

People are figuring this problem out very quickly, therefore the explosion of agentic capabilities happening right now even though the base model fundamentally does the same stuff as GPT4.

Re: Claude Code SDK

#115

Post by weikju »

cortesoft wrote: post #102
jdmoreira wrote: post #22

Earlier quoted context omitted.

Not sure about that golden end state. Mine would be being in a room surround by screens with AI agents coding, designing, testing, etc. I would be there in the center giving guidance, direction, applying taste, etc… All conversational, wouldn’t need to touch the keyboard 99% of the time. That's what I want and look forward one day

Basically the Star Trek model of computing.

All that’s really needed for this to work is a team of writers and plot conveniences.

Re: Claude Code SDK

#117

Post by yahoozoo »

pjmlp wrote: post #72
d_watt wrote: post #8

The way Claude Code is going is exactly what I want out of a agentic coding tool with this "unix toolish" philosophy. I've been using Claude code since the initial public preview release, and have seen the direction over time. The "golden" end state of coding agents is that you give it a Feature Request (EG Jira ticket), and it gives you a PR to review and give feedback on. Cursor, windsurf, etc, are dead ends in tha…

The moment I am able to outsource work for Jira tickets to a level that AI actually delivers a reasonable pull request, many corporate managers will seriously wonder why keep the offshoring team around.

Why would they pay you six figures to outsource to AI when they could pay offshore a fraction of that to do the same?

Re: Claude Code SDK

#118

Post by chamomeal »

jdmoreira wrote: post #22
d_watt wrote: post #8

The way Claude Code is going is exactly what I want out of a agentic coding tool with this "unix toolish" philosophy. I've been using Claude code since the initial public preview release, and have seen the direction over time. The "golden" end state of coding agents is that you give it a Feature Request (EG Jira ticket), and it gives you a PR to review and give feedback on. Cursor, windsurf, etc, are dead ends in tha…

Not sure about that golden end state. Mine would be being in a room surround by screens with AI agents coding, designing, testing, etc. I would be there in the center giving guidance, direction, applying taste, etc… All conversational, wouldn’t need to touch the keyboard 99% of the time. That's what I want and look forward one day

That sounds like torture for me lol

Re: Claude Code SDK

#119

Post by skydhash »

all2 wrote: post #62
Wowfunhappy wrote: post #38

Earlier quoted context omitted.

Voicemail universally sucks. However, when you're having a synchronous conversation with actual people, do you prefer to do everything via IM, or would you prefer a phone call?

Email. Async comms make sense 99% of the time at my job. Unless there's deep work to be done, or pie-in-the-sky idea fabricating. Or rubber-ducky sessions. But I won't do those with AI.

Email is Calm Technology[0] for collaborative knowledge work, where you expected to spend hours on a single task. If something needs brainstorming, or quick back and forth, you jump on a more synchronous type of conversation (IM, call, in person meeting).

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

Re: Claude Code SDK

#120

Post by kristopolous »

simonw wrote: post #24
baalimago wrote: post #23

Hasn't this been invented already in multiple shapes and forms..? I wrote my own version clai[1] over a year ago which does exactly this, only that it has tools support + is multi vendor. [1]: https://github.com/baalimago/clai

Looks quite similar to my https://llm.datasette.io tool as well. Honestly though, CLI tools for accessing LLMs (including piping content in and out of them) is such a clearly good idea I'm glad to see more tools implementing the pattern.

What is really needed is a usable multiplexed pipeline management and event system.

Then you can instrument through metaprogramming. For instance, an alert system could be:

"If the threshold goes over 1.0, contact the on-call person through their preferred method" - which may work ... maybe.

Or:

if any( "check_condition {x}", condition_set ): find_person("on call", right now).contact("preferred")

... the point is to divide everything up into small one-shots, parallelize them, use it as glue/api. Then you get composability. If you can get a framework for coroutines going then it's real game on. The final step is "needs based pulling" which is an inversion of mcp - contextual streams as event based sub-systems.

Things are still too slow for this to be not painful but that won't be the case forever.

Currently everything is linear. Doesn't have to be ... really doesn't.

Post reply on HN