Thank you so much for that excellent summary, I updated the gist :)
Here's what GPT-4 suggests: "Cents & Sensibility: The Ledger Luminaries'
Revolution":
Given the creative and innovative approach to leveraging large language
> models for categorizing and managing financial transactions without the
> traditional overhead of machine learning models, and considering the
> request for a name delivered with a malapropism twist and a nod to the sass
> and empowerment vibes of a 1950s woke feminist perspective, a fitting name
> could playfully incorporate elements of finance, AI, and a touch of retro
> flair.
> How about calling it "Cents & Sensibility: The Ledger Luminaries'
> Revolution"? This name cheekily misappropriates the classic Jane Austen
> title, adding a punny twist that encapsulates the financial aspect
> ("Cents") and the wise application of AI technology ("Sensibility"). It
> suggests a transformative movement ("Revolution") led by enlightened
> individuals ("The Ledger Luminaries") who are savvy with both their pennies
> and their prose. The name exudes a blend of financial acumen, technological
> sophistication, and a dash of old-school feminist charm, alluding to a
> novel approach in personal finance management with a tip of the hat to the
> past's pioneering spirits.
On Mon, Mar 11, 2024 at 10:13 AM Chary Chary <[email protected]> wrote:
> Interesting idea! Does it have a special name?
>
> So, effectively we have options:
>
>
> - Train ML model on our historical data and historical classifications
> - Ask existing LLM to classify transactions (some privacy issues here)
> - Ask LLM to write a deterministic code to classify (your example)
>
>
>
> On Monday, March 11, 2024 at 2:28:39 PM UTC+1 [email protected] wrote:
>
>> Yup, you nailed it! That's the idea :) it just saves time from worrying
>> about building a machine learning model, because we all have access to a
>> big one in the form of a large language model (Google/OpenAI are paying the
>> electricity cost).
>>
>> So this can help save time by removing the overhead and creating a
>> "deterministic" classifier in the form a python program that is likely more
>> concise, maintainable, and interpretable than machine learning models
>> trained for this task.
>>
>>
>>
>> On Mon, Mar 11, 2024 at 7:03 AM Chary Chary <[email protected]> wrote:
>>
>>> Hi,
>>>
>>> I briefly scanned through the article.
>>>
>>> So in the essence you give LLM a bunch some CSV example and then ask LLM
>>> to write a python code, which would categorize similar, based on the
>>> keywords.
>>>
>>> So, this is a kind of alternative to teaching ML model based on the
>>> previous transactions to be able to categorize new ones.
>>>
>>> Did it get the main idea correctly?
>>>
>>> On Monday, March 11, 2024 at 12:36:00 AM UTC+1 [email protected] wrote:
>>>
>>>> Made a quick prompt over the weekend:
>>>> https://gist.github.com/jaanli/1f735ce0ddec4aa4d1fccb4535f3843f
>>>>
>>>> Results are that my partner (someone non-technical, design background,
>>>> but familiar with prompt engineering) can use the prompts—the last thing I
>>>> would want is an inscrutable system that I manually built to import
>>>> transactions from our dozen institutions across multiple countries &
>>>> currencies, that they can't re-use or extend.
>>>>
>>>> Visual Studio Code and the Beancount extension are already a stretch
>>>> for them so having something that works with a single prompt at a time and
>>>> copy and pasting was my goal.
>>>>
>>>> Hope this helps someone else! Surprised that these tools are not easier
>>>> to use (and thank you for beancount, this wouldn't be possible otherwise :)
>>>>
>>>> Would be fun to extend this with DSPy (
>>>> https://github.com/stanfordnlp/dspy/blob/main/intro.ipynb) which could
>>>> likely help squeeze several different converters into a few signatures
>>>> (compressed prompts), and things like chain-of-thought prompting (iterative
>>>> runs of large language models) would further reduce the
>>>> extract-transform-load overhead that has kept me from trying beancount all
>>>> these years.
>>>>
>>>> Very best,
>>>> Jaan
>>>>
>>> --
>>> You received this message because you are subscribed to a topic in the
>>> Google Groups "Beancount" group.
>>> To unsubscribe from this topic, visit
>>> https://groups.google.com/d/topic/beancount/aoZ7-H1tCX4/unsubscribe.
>>> To unsubscribe from this group and all its topics, send an email to
>>> [email protected].
>>> To view this discussion on the web visit
>>> https://groups.google.com/d/msgid/beancount/eefe5ba4-c0cd-46cd-9fb8-8922b399c221n%40googlegroups.com
>>> <https://groups.google.com/d/msgid/beancount/eefe5ba4-c0cd-46cd-9fb8-8922b399c221n%40googlegroups.com?utm_medium=email&utm_source=footer>
>>> .
>>>
>> --
> You received this message because you are subscribed to a topic in the
> Google Groups "Beancount" group.
> To unsubscribe from this topic, visit
> https://groups.google.com/d/topic/beancount/aoZ7-H1tCX4/unsubscribe.
> To unsubscribe from this group and all its topics, send an email to
> [email protected].
> To view this discussion on the web visit
> https://groups.google.com/d/msgid/beancount/45eb3d9e-fd7c-4ad5-a36b-f9d3f3ac411fn%40googlegroups.com
> <https://groups.google.com/d/msgid/beancount/45eb3d9e-fd7c-4ad5-a36b-f9d3f3ac411fn%40googlegroups.com?utm_medium=email&utm_source=footer>
> .
>
--
You received this message because you are subscribed to the Google Groups
"Beancount" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to [email protected].
To view this discussion on the web visit
https://groups.google.com/d/msgid/beancount/CAKLvh_TvGBY3_%3D4fh3zjfFcLp04cZE8D_%2Ba_9QF-wCGDP8CjEQ%40mail.gmail.com.
