Hacker Timesnew | past | comments | ask | show | jobs | submit | terhechte's commentslogin

Thank you for NeoVim! I also use it every day, mostly for thinking / text / markdown though these days.

Have you compared against MLX? Sometimes I’m getting much faster responses but it feels like the quality is worse (eg tool calls not working, etc)


> Have you compared against MLX?

I don't think MLX supports similar 2-bit quants, so I never tried 397B with MLX.

However I did try 4-bit MLX with other Qwen 3.5 models and yes it is significantly faster. I still prefer llama.cpp due to it being a one in all package:

- SOTA dynamic quants (especially ik_llama.cpp) - amazing web ui with MCP support - anthropic/openai compatible endpoints (means it can be used with virtually any harness) - JSON constrained output which basically ensures tool call correctness. - routing mode


you can also use Claude Code programmatically with the `prompt` parameter in the cli.

And they can ban your account if they think you are doing that. I think someone even commented here on HN they were banned by Anthropic for this.

Why would they have that feature in claude code cli if it goes against the ToS? You can use Claude Code programatically. This is not the issue. The issue is that Anthropic wants to lock you in within their dev ecosystem (like Apple does). Simple as that.

allowed shell pipes doesn't necessarily mean they want loops running them.

One of the economic tuning features of an LLM is to nudge the LLM into reaching conclusions and spending the tokens you want it to spend for the question.

presumably everyone running a form of ralph loop against every single workload is a doomsday situation for LLM providers.


> allowed shell pipes doesn't necessarily mean they want loops running them.

insane that people apologize for this at all. we went from FOSS software being standard to a proprietary cli/tui using proprietary models behind a subscription. how quickly we give our freedom away.


Anthropic itself advertised their own implementation of agentic loop (Ralph plugin). Sure, it worked via their official plugin, but the end result for Anthropic would be the same.

There's nothing in TOS that prevents you from running agentic loops.


I don't know why this is downvoted, see my nephew (?) comment [0] for a longer version, but this is not at all clear IMHO. I'm not sure if a "claude -p" on a cron is allowed or not with my subscription, if I run it on another server is it? Can I parse the output of claude (JSON) and have another "claude -p" instance work on the response? It's only a hop, skip, and a jump over to OpenClaw it seems, which is _not_ allowed. But at what point did we cross the line?

It feels like the only safe thing to do is use Claude Code, which, thankfully, I find tolerable, but unfortunate.

[0] https://qht.co/item?id=47446703


is this against their tos or something? what did they expect programmers to do, not automate the automated code-writer?

Or the Python or Typescript Agent SDK libraries: https://platform.claude.com/docs/en/agent-sdk/overview

Or can you? It's my understanding that you cannot use your subscription with the Agent SDK, that's what the docs say:

> Unless previously approved, Anthropic does not allow third party developers to offer claude.ai login or rate limits for their products, including agents built on the Claude Agent SDK. Please use the API key authentication methods described in this document instead.

Though there was that tweet [0] a while back by someone from Anthropic that just muddied the water. It's frustrating because I feel like the line between the Agent SDK and `claude -p` is not that large but one can use the subscription and one can't... or we don't know, the docs seem unambiguous but the tweet confuses things and you can find many people online saying you can, or you can't.

I'd love to play around with the Agent SDK and try out some automations but it seems I can only do that if I'm willing to pay for tokens, even though I could use Claude Code to write the code "for" the Agent SDK, but not "run" the Agent SDK.

Where is the line? Agent SDK is not allowed with subscription, but if I write a harness around passing data to and parsing the JSON response from `claude -p '<Your Prompt>' --output-format json` would that be allowed? If I run it on a cron locally? I literally have no idea and, not wanting my account to be banned, I'm not interested in finding out. I wish they would clarify it.

[0]

Twitter: https://x.com/trq212/status/2024212378402095389

XCancel: https://xcancel.com/trq212/status/2024212378402095389

Text:

> Apologies, this was a docs clean up we rolled out that’s caused some confusion.

> Nothing is changing about how you can use the Agent SDK and MAX subscriptions!

> We want to encourage local development and experimentation with the Agent SDK and claude -p.

> If you’re building a business on top of the Agent SDK, you should use an API key instead. We’ll make sure that’s clearer in our docs.


Yes.

> Unless previously approved, Anthropic does not allow third party developers to offer claude.ai login or rate limits for their products

So you can't offer a product based on the subscription. I replied to a comment proposing to use the CLI with --prompt:

> you can also use Claude Code programmatically with the `prompt` parameter in the cli.

And I just informed that Agent SDK is a much nicer way to do that. For internal use or whatever the ToS allows.


Yea I am this exact boat - it's insane how unclear it is. Why have the -p option at all if they don't want it to be called by other processes?

If they only want people using claude code inside their harness, they could... just remove -p?


ChatGPT allows setting a "personality" profile Settings -> "Base style and tone". Try the "Efficient" setting. Its great. no emoji, no clickbait.

How is Peter "early in their career"? When he sold PSPDFKit for 100mio in 2020 he had been working on it for 13 years, and before that he'd worked as an engineer.

Any proof for this claim?


Shuru should do exactly what you want:

https://shuru.run


Did you try an MLX version of this model? In theory it should run a bit faster. I'm hesitant to download multiple versions though.


Haven't tried. I'm too used to llama.cpp at this point to switch to something else. I like being able to just run a model and automatically get:

- OpenAI completions endpoint

- Anthropic messages endpoint

- OpenAI responses endpoint

- A slick looking web UI

Without having to install anything else.


Is there a reliable way to run MLX models? On my M1 Max, LM Studio seems to output garbage through the API server sometimes even when the LM Studio chat with the same model is perfectly fine. llama.cpp variants generally always just work.


so your definition of consciousness is having petty emotions?


I agree that macOS has become worse, however your examples don't really count:

Window snapping was implemented some time ago: https://www.macrumors.com/2024/06/12/macos-sequoia-window-ti...

Instead of win key, you can press F3, or just set a hotkey that works for you in the System Preferences

Instead of clicking the red maximize button, you can double-click the window header / title. This will use an algorithm to try to resize the window to the best size for its content.


Option-click green button does window maximise (normal click does full-screen)


Technically it’s zoom, and how it functions is dependent on the app. In Finder it used to resize the window to a size that contained all the icons. Clicking it again would revert the window size.


Ah I wish I knew that, thanks for the tip!


You can also hold ALT and press the green button to mazimze.


The app still gets to decide though! Most programs do go full size with an alt+green click, but not all. A column-style Finder window, for example, seems to go taller but no wider.


Maximize is green. (Any chance you might be color blind?)


Green is “Zoom window to fit content”, not Maximize.


That changed many OS versions ago.


I like doing side projects, I don't like wasting a day of work potential on any of these web apps: Google Cloud, AWS, Azure, Appstore Connect, Google's Android App Store, RevenueCat, Stripe, etc

I dread having to log in to these systems and waste hours achieving the simplest tasks.

This is what I'm using Claude for. E.g. I log in to AppStore connect, tell it what I need (3 subscription tiers), it will do all the clicking and editing and Apple's stupid UI, then I will ask it to create a summary for RevenueCat, and use another Claude session in there to click all the buttons to configure based on what just happened in Appstore connect.

Or configuring S3 buckets or whatnot.


Could you detail this a bit please


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

Search: