←back to thread

Show HN: Spegel, a Terminal Browser That Uses LLMs to Rewrite Webpages

(simedw.com)
422 points simedw | 6 comments | 01 Jul 25 12:49 UTC | HN request time: 1.168s | source | bottom
Show context
bubblyworld ◴[01 Jul 25 13:15 UTC] No.44433602[source]▶
Classic that the first example is for parsing the goddamn recipe from the goddamn recipe site. Instant thumbs up from me haha, looks like a neat little project.
replies(3): >>44435722 #>>44436466 #>>44438277 #
andrepd ◴[01 Jul 25 16:44 UTC] No.44435722[source]▶
Which it apparently does by completely changing the recipe in random places including ingredients and amounts thereof. It is _indeed_ a very good microcosm of what LLMs are, just not in the way these comments think.
replies(3): >>44435998 #>>44436175 #>>44436268 #
1. simedw ◴[01 Jul 25 17:28 UTC] No.44436175[source]▶
It was actually a bit worse than that the LLM never got the full recipe due to some truncation logic I had added. So it regurgitated the recipe from training, and apparently, it couldn't do both that and convert units at the same time with the lite model (it worked for just flash).

I should have caught that, and there are probably other bugs too waiting to be found. That said, it's still a great recipe.

replies(1): >>44437152 #
2. ◴[01 Jul 25 23:23 UTC] No.44438851[source]▶
3. 0x696C6961 ◴[01 Jul 25 23:24 UTC] No.44438859[source]▶
What is the point?
replies(2): >>44439718 #>>44444323 #
4. plonq ◴[02 Jul 25 02:21 UTC] No.44439718{3}[source]▶
I’m someone else but for me the point is a serious bug resulted _incorrect data_, making it impossible to trust the output.
replies(1): >>44440736 #
5. bubblyworld ◴[02 Jul 25 06:22 UTC] No.44440736{4}[source]▶
Assuming you are responding in good faith - the author politely acknowledged the bug (despite the snark in the comment they responded to), explained what happened and fixed it. I'm not sure what more I could expect here? Bugs are inevitable, I think it's how they are handled that drives trust for me.
6. andrepd ◴[02 Jul 25 14:38 UTC] No.44444323{3}[source]▶
The point is LLMs are fundamentally unreliable algorithms for generating plausible text, and as such entirely unsuitable for this task. "But the recipe is probably delicious anyway" is beside the point, when it completely corrupted the meaning of the original. Which is annoying when it's a recipe but potentially very damaging when it's something else.

Techies seem to pretend this doesn't happen, and the general public who doesn't understand will trust the aforementioned techies. So what we see is these tools being used en masse and uncritically for purposes to which they are unsuited. I don't think this is good.