Web-Projects/blog-static
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Make some edits.

Browse Source 
Signed-off-by: Danila Fedorin <danila.fedorin@gmail.com>
This commit is contained in:
Danila Fedorin
2026-04-05 15:42:26 -07:00
parent a278d1f572
commit 21463ede20
1 changed files with 15 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files

42
content/blog/pdf_flashcards_llm/index.md
View File

@@ -254,22 +254,12 @@ With LLMs, I was able --- allowed? --- to view things more so from the
end-user perspective. I didn't know, and didn't need to know, the API end-user perspective. I didn't know, and didn't need to know, the API
for `PyMuPDF`, `argostranslate`, or `spaCy`. I didn't need to understand for `PyMuPDF`, `argostranslate`, or `spaCy`. I didn't need to understand
the PDF format. I could move one step away from the nitty-gritty and focus the PDF format. I could move one step away from the nitty-gritty and focus
on the 'why' and the 'what'. on the 'why' and the 'what', on the challenge of what I wanted to accomplish.
I wrestled with the inherent complexity and
The boundary between 'manual' and 'automatic' was not always consistent. avoided altogether the unrelated difficulties that merely happened to be
Though I didn't touch any of the PyMuPDF code, I did need to look fairly
closely at the logic that classified my squiggles as "underlines" and found
associated words. In the end, though, I was able to focus on the core
challenge of what I wanted to accomplish (the inherent complexity) and
avoid altogether the unrelated difficulties that merely happened to be
there (downloading language modules; learning translation APIs; etc.) there (downloading language modules; learning translation APIs; etc.)
This was true even when I was writing the code myself. Codex created the By enabling me to do this, the LLM let me make rapid progress, and to produce
word-highlighting utility in one shot in a matter of seconds, saving
me probably close to an hour of interpreting the algorithm's outputs
while I iterated on the proper heuristic.
By enabling me to _do_, the LLM let me make rapid progress, and to produce
solutions to problems I would've previously deemed "too hard" or "too tedious". solutions to problems I would've previously deemed "too hard" or "too tedious".
This did, however, markedly reduce the care with which I was examining This did, however, markedly reduce the care with which I was examining
the output. I don't think I've _ever_ read the code that produces the the output. I don't think I've _ever_ read the code that produces the
@@ -279,17 +269,8 @@ I think that this has to do, at least in part, with different views
on code as a medium. on code as a medium.
#### The Builders and the Craftsmen #### The Builders and the Craftsmen
AI discourse is nothing new; others before me have identified a distinction There are two perspectives through which one may view software:
between individuals that seems to color their perspective on LLMs. Those as a craft in and of itself, and as a means to some end.
that appreciate writing software as a craft, treating code as an end
in and of itself (at least in part), tend to be saddened and repulsed by
the advent of LLMs. LLMs produce "good enough" code, but so far it
lacks elegance, organization, and perhaps, care. On the other hand,
those that treat software as a means to an end, who want to see their
vision brought to reality, view LLMs with enthusiasm. It has never been
easier to make something, especially if that something is of a shape
that's been made before.
My flashcard extractor can be viewed in vastly different ways when faced My flashcard extractor can be viewed in vastly different ways when faced
from these two perspective. In terms of craft, I think that it is at best from these two perspective. In terms of craft, I think that it is at best
mediocre; most of the code is generated, slightly verbose and somewhat mediocre; most of the code is generated, slightly verbose and somewhat
@@ -305,7 +286,7 @@ capable of being any combination of these two camps at any given time. Indeed,
different sorts of software demand to be viewed through different lenses. different sorts of software demand to be viewed through different lenses.
I will _still_ treat work on my long-term projects as craft, because I will _still_ treat work on my long-term projects as craft, because
I will come back to it again and again, and because our craft has evolved I will come back to it again and again, and because our craft has evolved
and to engender stability and maintainability. to engender stability and maintainability.
However, I am more than happy to settle for 'underwhelming' when it means an However, I am more than happy to settle for 'underwhelming' when it means an
individual need of mine can be addressed in record time. I think this individual need of mine can be addressed in record time. I think this
@@ -332,7 +313,7 @@ the number of features it provides. Suppose also that individual users
leverage only a small subset of the software's functionality. From these leverage only a small subset of the software's functionality. From these
assumptions it would follow that individual programs, made to serve a single assumptions it would follow that individual programs, made to serve a single
user's need, would be significantly less complicated than the "whole". user's need, would be significantly less complicated than the "whole".
By definitions, these programs would also be better tailored to the users' By definition, these programs would also be better tailored to the users'
needs. With LLMs, we're getting to a future where this might be possible. needs. With LLMs, we're getting to a future where this might be possible.
I think that my flashcard generator is an early instance of such software. I think that my flashcard generator is an early instance of such software.
@@ -393,12 +374,17 @@ to hit the ground running, to know what to ask and to help pluck out a particula
solution from the space of various approaches. I think that this greatly solution from the space of various approaches. I think that this greatly
accelerates the effectiveness of using LLMs compared to non-technical experts. accelerates the effectiveness of using LLMs compared to non-technical experts.
For another, the boundary between 'manual' and 'automatic' is not always consistent.
Though I didn't touch any of the `PyMuPDF` code, I did need to look fairly
closely at the logic that classified my squiggles as "underlines" and found
associated words. It was not enough to treat LLM-generated code as a black box.
Another advantage software folks have when leveraging LLMs is the established Another advantage software folks have when leveraging LLMs is the established
rigor of software development. LLMs can and do make mistakes, but so do people. rigor of software development. LLMs can and do make mistakes, but so do people.
Our field has been built around reducing these mistakes' impact and frequency. Our field has been built around reducing these mistakes' impact and frequency.
Knowing to use version control helps turn the pathological downward spiral Knowing to use version control helps turn the pathological downward spiral
of accumulating incorrect tweaks into monotonic, step-wise improvements. of accumulating incorrect tweaks into monotonic, step-wise improvements.
Knowing how to construct a test suite and thinking about edge cases cap Knowing how to construct a test suite and thinking about edge cases can
provide an agent LLM the grounding it needs to iterate rapidly and safely. provide an agent LLM the grounding it needs to iterate rapidly and safely.
In this way, I think the dream of personal software is far from being realized In this way, I think the dream of personal software is far from being realized