Viewing profile — ggnore7452

Isn't that the memory files are loading by default?

too bad that only the smaller on-device models support native audio input.

imo, for health related stuff. or most of the general knowledge doesn't require latest info after 2023. the internal knowledge of LLM is so much better than the web search augmente…

I’m fine with hires without degrees. But if Google still filters people with LeetCode style coding questions, what’s the point of that in this day and age?

so immersive i actually hit ctrl+w and closed the whole tab.

I’ve done a similar PDF → Markdown workflow. For each page: - Extract text as usual. - Capture the whole page as an image (~200 DPI). - Optionally extract images/graphs within the …

I’ve been using LLMs for this kind of geo-guessing since Gemini 2.0. Even without access to internet search like o3, they perform surprisingly well.

appreciate the question on hparams for websearch! one of the main reasons i build these ai search tools from scratch is that i can fully control the depth and breadth (and also cus…

How’s this compare to likes of Fish audio? Wish they support voice clone using longer audio tho . Haven’t looked into this space for few months , but iirc, previously SOTA was like…

anyone tried this? is this actually overall better than xgboost/catboost?

if anything i would consider embeddings bit overrated, or it is safer to underrate them. They're not the silver bullet many initially hoped for, they're not a complete replacement …

What’s more interesting to me here are the calibration graphs: • LLMs, at least GPT models, tend to overstate their confidence. • A frequency-based approach appears to achieve cali…

Side note: I feel like ChatGPT's long-term memory isn't implemented properly. If you check the 'saved memories,' they are just bad.

question: any good on-device size image embedding models? tried https://github.com/unum-cloud/uform which i do like, especially they also support languages other than English. Any …

I've been working on a small personal project similar to this and agree that replicating the overall experience provided by Perplexity.ai, or even improving it for personal use, is…

more on the LPU and data center: https://wow.groq.com/lpu-inference-engine/ price and speed benchmark: https://wow.groq.com/

The Groq demo was indeed impressive. I work with LLM alot in work, and a generation speed of 500+ tokens/s would definitely change how we use these products. (Especially considerin…

it still works well with other LLM (like llama and more). various small, open sourced, and verticle LLMs vs one large GPT models would be quite interesting.

The place where I work was an early adopter of LLM, having started working on it a year ago. When I build stuff with GPT-3, especially in the earlier days, I get the strong impress…

there is actually a paper by OpenAI themselves on summarizing long document. essentially, break a longer text into smaller chunks, and run a multi-stage sequential summarization. e…

I use large language model for work and use Notion daily. while I like the "AI" part (the large language model), think it would be more interesting and productive to use same backe…

AlphaStar is really amazing achievement. but this is not like AlphaZero for Go, which completely made people rethink how Go should be played. AlphaStar didn't "solved" SC2. It can …

also, for some quick and simple Q&A system. Haystack https://github.com/deepset-ai/haystack (essentially dense vector similarity on Elastic Search) looks pretty promising and suppo…

kinda interesting see people use "authoritarian" as if it's all the reasons China succeed (in term of infra, econ, and general well-being), and therefore nothing to see and learn. …