Deepseek AI for Tax / Accounting (vs. ChatGPT + others)

[@samuelotto7418]

Ok I did this by hand and noticed my number came in a lot lower than these at $148,644. Found the difference. The Deepthink and ChaptGPT models are missing a BIG deduction. The Qualified Business Income (QBI) deduction. I understand there is the 50% W-2 or 2.5% UBIA phaseout that kicks in at $380,000 taxable income for MFJ. However, in this scenario the QBI deduction would be worth probably about $84,868 in deduction. With such a large deduction the AI should have asked clarifying questions otherwise at the 35% tax rate they're leaving about $29,700 on the table. Also should be noted I used 2024 tax brackets.

[@HectorGarciaCPA]

Thanks!... there you go... There are two big questions here, which is wether the two K-1's and Schedule C would qualify for QBI

[@t2p5g4]

Very informative video. Thank you. I am in Canada and had a client with a German Pension. I needed to translate it into English. We scanned it as a first step. I found that Claude worked best, because it could use a fixed width font in the artifacts window to replicate the columns.

[@HectorGarciaCPA]

I like Claude for that stuff

[@t2p5g4]

I wonder if you could upload all the applicable IRS publications to notebook LLM and see how it could do.

[@HectorGarciaCPA]

In Theory yes, thats what TaxGPT and CPApilot is for

[@AnuragSingh-zn3nu]

so who's the most accurate according to the your calculation?

[@HectorGarciaCPA]

They were technically all OFF, as none of them considered QBI, but that can easily be trained.

[@AnuragSingh-zn3nu]

@@HectorGarciaCPA thank you.

[@pluggedinprofits.]

Thank you Hector, this was fantastic test. Good to know that our clients will as confused as us till further notice 🤣 Also, i personally ranked Deepseek and Claude over gpts heck even perplexity over gpt.

[@fernandoortiz6069]

what is the correct amount?

[@HectorGarciaCPA]

none of those were 100%... but ChatGPT o1 and DeepThink R1 were closest

[@kalusallisudusalli772]

You need to click the deepsek search button to get the current values

[@HectorGarciaCPA]

I did click on that

[@marvinsafi]

thanks for sharing

[@HectorGarciaCPA]

You're welcome!

[@mbohdanowicz77]

For context these are zero shot questions with no guidance or input sources. Wrappers are done.

[@HectorGarciaCPA]

Wrappers?

[@tamanpara2682]

I think he means the accounting profession is about to be decimated if not obliterated by these AI learning models. Ditto design engineering. About to get a lot less costly for the end customer of these high end services.

[@tamanpara2682]

​@@HectorGarciaCPAI think he means the accounting profession is about to be decimated if not obliterated by these AI learning models. Ditto design engineering. About to get a lot less costly for the end customer of these high end services.

[@mbohdanowicz77]

@HectorGarciaCPA fellow beancounter here. A wrapper is a pre-configured app/front-end that uses a frontier model such as open AI or Gemini as it's "brain". Pre configured directions/instructions on its purpose and output with structured sources to draw on, such as state and federal tax libraries or case precedents. This improves the quality of the response.

[@HectorGarciaCPA]

@ and you think with Deepseek those wrappers are toast?

[@nuqwestr]

Running locally vs Subscription model. R1 still needs the large language model.

[@HectorGarciaCPA]

I did not run it locally, I used all the webbased tools in this video

[@nuqwestr]

@@HectorGarciaCPA I'm confused then, it is my understanding R1 requires LLMs to be taught before it runs, faster yes, but still requires the subscription based data?

[@nuqwestr]

R1 runs on your home based chipset, Groq is a specifically designed chipset for LLM?

[@nuqwestr]

To run **DeepSeek R1**, the minimum chipset requirements depend on the model size you're using. Here are the general requirements: - **For the 7 billion parameter model**: At least an **NVIDIA RTX 3060** with **12GB of VRAM**. - **For the 33 billion parameter model**: At least an **NVIDIA RTX 4080** with **16GB of VRAM**.

[@nuqwestr]

RTX 3060 for $300 or A100 for $9,000