HackerTrans
TopNewTrendsCommentsPastAskShowJobs

amarble

312 karmajoined 5 lat temu

Submissions

LLMs are still just low code / no code software

marble.onl
2 points·by amarble·5 godzin temu·0 comments

[untitled]

1 points·by amarble·wczoraj·0 comments

There is minimal downside to switching to open models

marble.onl
407 points·by amarble·20 dni temu·330 comments

AI doesn't replace white collar work

marble.onl
67 points·by amarble·4 miesiące temu·104 comments

[untitled]

1 points·by amarble·5 miesięcy temu·0 comments

I paid $170 and all I got was this demo

marble.onl
3 points·by amarble·5 miesięcy temu·1 comments

I paid $170 and all I got was this stupid demo

marble.onl
1 points·by amarble·5 miesięcy temu·0 comments

Task-free intelligence testing of LLMs

marble.onl
69 points·by amarble·6 miesięcy temu·22 comments

Task-free intelligence testing of LLMs

marble.onl
1 points·by amarble·6 miesięcy temu·0 comments

Intelligence is not just about task completion

marble.onl
1 points·by amarble·6 miesięcy temu·0 comments

If You Meet ET in Space, Kill Him (2024)

nautil.us
3 points·by amarble·6 miesięcy temu·0 comments

Intelligence is not just about task completion

marble.onl
3 points·by amarble·6 miesięcy temu·0 comments

Show HN: Gen AI Writing Showdown

writing-showdown.com
2 points·by amarble·7 miesięcy temu·0 comments

Ifrro member Kopinor signs agreement on newspaper content for AI in Norway

ifrro.org
2 points·by amarble·7 miesięcy temu·0 comments

Comparing language model performance on creative writing transformations

writing-showdown.com
2 points·by amarble·7 miesięcy temu·0 comments

Eminembench

marble.onl
1 points·by amarble·9 miesięcy temu·0 comments

Promptware Attacks Against LLM-Powered Assistants in Production

sites.google.com
1 points·by amarble·10 miesięcy temu·0 comments

comments

amarble
·4 miesiące temu·discuss
The point of a discussion site is to hear what other people think and get different perspectives. Just getting an LLM's insightful, well-thought-out response isn't really a big draw, if one is looking for that, there's a pretty obvious way to get it. I posted this the other day (ignore the title I realized later it's too clickbaity) but this is why IMO LLMs won't replace the workforce, people aren't looking for answers to things, they're looking for other people's takes: https://news.ycombinator.com/item?id=47299988
amarble
·5 miesięcy temu·discuss
As a counterpoint, I also tried writing something with Claude last weekend: a Google docs clone[1]. I spent $170 on Anthropic API credits, and got something that did mostly what I asked but was basically useless. It seems that for simple interfaces for which there is an exact specification, like the recent compiler and web browser examples, it's possible to write bigger projects that "work" as a demo although not in a way they'd be viable alternatives. For anything that requires taste and judgment, we've still got a long way to go. There are lots of great demos out there but few if any real examples of vibe coded (or whatever you want to call it) software standing alone as an alternative to project people wrote.

[1] https://www.marble.onl/posts/this_cost_170.html
amarble
·5 miesięcy temu·discuss
This weekend I tried what I'd call a medium scale agentic coding project[0], following what Anthropic demonstrated last week autonomously building a C-compiler [1]. Bottom line is, it's possible to make demos that look good, but it really doesn't work well enough to build software you would actually use. This naturally lends itself to the "everybody is taking about how great it is but nobody is building anything real with it" construct we're in right now. It is great, but also not really useful.

[0] https://www.marble.onl/posts/this_cost_170.html

[1] https://www.anthropic.com/engineering/building-c-compiler
amarble
·8 miesięcy temu·discuss
Since we're sharing, I have a "claude" command that lets me get quick answers but also saves the conversation and outputs an identifier so in the rare case I want a follow-up, I can ask a question with the ID to continue the conversation.

https://gist.github.com/rbitr/bfbc43b806ac62a5230555582d63d4...