Silicon Investor (SI) -- The First Internet Community

STOCKTALK

We've detected that you're using an ad content blocking browser plug-in or feature. Ads provide a critical source of revenue to the continued operation of Silicon Investor. We ask that you disable ad blocking while on Silicon Investor in the best interests of our community. If you are not using an ad blocker but are still receiving this message, make sure your browser's tracking protection is set to the 'standard' level.

Strategies & Market Trends : Technical analysis for shorts & longs -- Ignore unavailable to you. Want to Upgrade?

To: E_K_S who wrote (64141)	6/27/2025 12:20:54 PM
From: Johnny Canuck	1 Recommendation Recommended By E_K_S Read Replies (1) \| Respond to of 69062

For stock and economic research I have been using Perplexity.ai. It is free and seems to generally have good results. I especially like the fact it exposes the chain of thought so you can see the process it is doing. By the way there have been papers that suggest adding the phrase to your prompt "show the chain of thought of the process" prevents some errors from occurring. For work we have started to use ChatGPT for certain things. It seems better at summarizing large documents or merging documents together. We don't use it for work that has intellectual property concerns as it adds the information to its knowledge base. For example I asked some questions early on in the life of ChatGPT and I notice that response is the go to answer in that topic area as it is quite an obscure area of knowledge. For playing around you can use LM Studio to run local models that do not share you data. I am running DeepSeek locally, derived from Meta's LLAMA. I find it is not as good at summarizing text though. LM studio lets you load many open source models. Placing around each model has pros and cons.