Hacker News: emptiestplace

New comment by emptiestplace in "Interview with Jeff Atwood, Co-Founder of Stack Overflow"

emptiestplace — Sun, 26 Jan 2025 01:56:50 +0000

I had to think about this for a minute because the abstraction levels idea is very appealing, but ultimately I think this comparison is specious and misses the core issue entirely.

XY problem is a communication and problem-solving anti-pattern where someone has already decided on an approach and is just asking about implementation details, rather than being open to potentially better solutions that might emerge if they just explained wtf they are trying to do first. Framing it as different abstraction levels obscures this real issue and incorrectly suggests it's just a natural variation in thinking styles rather than a specific mistake in problem-solving approach.

New comment by emptiestplace in "Chatbox: Cross-platform desktop client for ChatGPT, Claude and other LLMs"

emptiestplace — Sun, 26 Jan 2025 01:19:48 +0000

Sorry, I was mistaken about having used LiteLLM - this is the one I was using: https://github.com/wangxj03/ai-cookbook.git, and you can see the hardcoded shit here: https://github.com/wangxj03/ai-cookbook/blob/main/anthropic-... - it does not actually restrict anything though, and like I said, I noticed it was getting slow when it was sending 100-200K token requests.

Also, it's pretty easy to find unresolved bugs related to openwebui not handling context length parameters correctly - I believe I actually read something from the author saying that this parameter is effectively disabled (for non-local LLMs maybe?).

New comment by emptiestplace in "Chatbox: Cross-platform desktop client for ChatGPT, Claude and other LLMs"

emptiestplace — Sat, 25 Jan 2025 08:19:32 +0000

I think that's probably the shim I was referring to - it has hardcoded context length, but it is either implemented incorrectly, Anthropic ignores it, or maybe it's on openwebui to manage the window and it just isn't? Not sure. I found it kept getting slow, so I was starting new conversations to work around that. Eventually I got suspicious and checked - I'd burned through almost $100 within a few hours.

LibreChat isn't as nice in some areas, but it's much more efficient in this regard.

New comment by emptiestplace in "Chatbox: Cross-platform desktop client for ChatGPT, Claude and other LLMs"

emptiestplace — Sat, 25 Jan 2025 08:08:29 +0000

Needs some usability testing - I suspect even five minutes of watching a non-technical user trying to use it would be very illuminating. UI is unintuitive throughout. Consider, one of the most frequent actions you will ever do in this type of app is start a new conversation, and here it is represented by a little button near the bottom of the sidebar where you might look for 'Settings' - apparently collapsing the sidebar is much more important. Tiny text, low contrast text, confusing collapsing/expanding sections, lack of whitespace and/or colour to differentiate message pair halves, confusing hover actions for copy, no floating or bottom of code block copy button... I'm pretty sure configuring API keys was weird for some reason as well, but I can't remember what it was.

New comment by emptiestplace in "Chatbox: Cross-platform desktop client for ChatGPT, Claude and other LLMs"

emptiestplace — Sat, 25 Jan 2025 06:23:28 +0000

LibreChat is probably the one you want to compare to - Claude is not supported by OpenWebUI, and the shim will cost you dearly in terms of tokens.

New comment by emptiestplace in "Chatbox: Cross-platform desktop client for ChatGPT, Claude and other LLMs"

emptiestplace — Sat, 25 Jan 2025 06:21:42 +0000

There is very little I find more frustrating than software that could so easily be nice to use but isn't.

New comment by emptiestplace in "Susctl CVE-2024-54507: A particularly 'sus' sysctl in the XNU kernel"

emptiestplace — Fri, 24 Jan 2025 01:13:19 +0000

To inspire more of the same.

New comment by emptiestplace in "DHS removes all members of cyber security advisory boards, halts investigations"

emptiestplace — Wed, 22 Jan 2025 09:58:45 +0000

> We don’t need the military-industrial complex

I hope you realize that part isn't going anywhere any time soon.

New comment by emptiestplace in "Interview with Jeff Atwood, Co-Founder of Stack Overflow"

emptiestplace — Wed, 22 Jan 2025 08:13:01 +0000

> Not everything is an XY problem

Pretty close, though.

New comment by emptiestplace in "Moving on from React, a year later"

emptiestplace — Wed, 22 Jan 2025 07:54:47 +0000

It's back, but the nice thing is it's 10x more complicated now!

New comment by emptiestplace in "David Lynch has died"

emptiestplace — Fri, 17 Jan 2025 03:36:16 +0000

Season 3 is so great it easily eclipses the first two, despite my pretty strong nostalgia-bias. It's like the first two were just a warm-up - and we needed the 25 years just to prepare ourselves for what he really wanted to do.

New comment by emptiestplace in "Test-driven development with an LLM for fun and profit"

emptiestplace — Thu, 16 Jan 2025 21:42:53 +0000

We've had failed projects since long before LLMs. I think there is a tendency for people to gloss over this (3.) regardless, but working with an LLM it tends to become obvious much more quickly, without investing tens/hundreds of person-hours. I know it's not perfect, but I find a lot of the things people complain about would've been a problem either way - especially when people think they are going to go from 'hello world' to SaaS-billionaire in an hour.

I think mastery of the problem domain is still important, and until we have effectively infinite context windows (that work perfectly), you will need to understand how and when to refactor to maximize quality and relevance of data in context.

New comment by emptiestplace in "GPT-4o with scheduled tasks (jawbone) is available in beta"

emptiestplace — Wed, 15 Jan 2025 02:35:30 +0000

I love the questioning my sanity before I've completely opened my eyes part. It's like a jump start to my day.

New comment by emptiestplace in "GPT-4o with scheduled tasks (jawbone) is available in beta"

emptiestplace — Tue, 14 Jan 2025 23:52:31 +0000

https://www.theverge.com/2025/1/9/24340238/apple-iphone-alar...

New comment by emptiestplace in "Scientist discover that AI has developed an uncanny human-like ability"

emptiestplace — Tue, 14 Jan 2025 15:38:39 +0000

> Consequently, for an LLM to predict the next word in a sentence generated by a human, it must model these processes.

No.

New comment by emptiestplace in "Pagecord: Publish your writing effortlessly from your inbox"

emptiestplace — Sun, 12 Jan 2025 06:30:05 +0000

What could go wrong?

New comment by emptiestplace in "Sam Altman's sister files lawsuits against Sam alleging sexual abuse"

emptiestplace — Wed, 08 Jan 2025 03:23:36 +0000

> I believe everything Annie says here.

How is this relevant?

New comment by emptiestplace in "Refurb Weekend: Atari Stacy"

emptiestplace — Mon, 06 Jan 2025 14:50:05 +0000

I think they removed it.

New comment by emptiestplace in "Parasitic worms 'manipulate' mantises onto asphalt roads, say researchers"

emptiestplace — Sat, 04 Jan 2025 20:23:34 +0000

I appreciate harm reduction but I think any such 'perfect' drug would lead to dehydration / starvation deaths, or at least a lot more people living on the streets.

New comment by emptiestplace in "Most people don't care about quality"

emptiestplace — Thu, 02 Jan 2025 14:16:04 +0000

Excellent joke explanation!