applgo443

What's the simple explanation for why these VLM OCRs hallucinate but previous version of OCRs don't?

Why are traditional OCRs better in terms of hallucination and confidence scores?

Can we use logprobs of LLM as confidence scores?

applgo443

2 tahun yang laludiscuss

When i deploy a webapp on azure, it expects me to put env variables in a file or their own tool (key value fields) where you can add env variables one by one.

Is there a way to use envelope in places like those?

applgo443

3 tahun yang laludiscuss

If it's 5 common crawls, isn't data across multiple common crawls mostly similar?

applgo443

3 tahun yang laludiscuss

Is ETL/ELT same as writing SQL scripts and periodically executing them? I assumed there's more to it.

applgo443

3 tahun yang laludiscuss

May be rewriting user's description might help you match code better?

Similar to the prompt engineering for previous era GPT completion models.

applgo443

3 tahun yang laludiscuss

How do you approach the problem of what files to look into to fix a bug? Just embeddings doesn't seem to cut it.

applgo443

3 tahun yang laludiscuss

How is your experience with Modal?

And I'm curious to know more about your costs of deployment and running on Modal.

applgo443

3 tahun yang laludiscuss

Did you consider first asking LLM to explain what a code snippet does and use that instead?

It'd significantly increase the costs though.

applgo443

3 tahun yang laludiscuss

I saw your comment, got curious, and looked at a lot of your old comments. Lots of interesting insights - Thanks for sharing them.

If you don't mind me asking, what do you do? I'm a researcher at FAANG working on language models and starting a new company in the space. Would love to connect. Feel free to email me - [email protected]

applgo443

3 tahun yang laludiscuss

Used OpenAI APIs before but not function calling. What's the use of function calling in this example?

applgo443

3 tahun yang laludiscuss

How does the confidence scores work?

applgo443

3 tahun yang laludiscuss

I’m a researcher in the space exploring few ideas with the intention of starting up. Would love to reach out to you and talk to you. Is there a way I can contact you?

My email is [email protected]

applgo443

3 tahun yang laludiscuss

I think we can detect atleast a few things like PII leaks etc. Don't you think those things alone are valuable?

applgo443

3 tahun yang laludiscuss

They mention the contextual stack is is relatively underdeveloped. Any idea on what can be improved there?

applgo443

3 tahun yang laludiscuss

What do you mean by firewall layer? What tools do you use here?

applgo443

3 tahun yang laludiscuss

Wow, if you're competing with ChatGPT, that gives all other startups out there hope that competitors aren't something to be super scared about :)

applgo443

3 tahun yang laludiscuss

Location: SF Bay Area

Remote: Preferred

Willing to relocate: Depends on opportunity

Technologies: Python, Pytorch, Tensorflow, Jax, machine learning, deep learning, language modeling,

Email: [email protected]

I'm a Research Engineer at Apple, working on Language Models. Have expertise in both building LMs + using these LM APIs to build apps. I'm adept at the fundamentals of machine learning, deep learning and worked across NLP (language models), NLP + CV (Image captioning), and reinforcement learning (PPO for image captioning, robot navigation, etc). I am also a proficient C++ systems developer and worked on several low level systems problems such as sorting, caching, etc before I entered ML space.

What I'm looking for: Though I'm primarily a research engineer, I'm interested in joining a place that lets me wear multiple hats, and gives me enough responsibility and opportunity to scale my personal learnings and skills along with that of the company. My mid term goal (~ 5 years) is to start my own company. Hence, for my next opportunity, I'd like to join a small startup where I can also learn the non-technical parts of building a company.

applgo443

4 tahun yang laludiscuss

Why are there so many weather APIs? What's going on here?

applgo443

4 tahun yang laludiscuss

I considered doing this - take screenshots of your screen constantly, OCR them and index them. It's fairly simple. However, there are some problems

- OCR constantly running in the background is power consuming - What granularity do you take your screenshots? Imagine each screenshot is 500 Kb and you take one each second. This'd result in 40 gigs of data per day. How are we gonna store it? How many days data do you want to keep?

Submissions

LLM Training Puzzles

Ask HN: What does it take to be a CTO?

Ask HN: As an engineer, how to learn handling interpersonal conflicts?

Ask HN: What Happened to Nike AR Fit?

Elon Musk and the Midwit Meme – Dalton Caldwell and Michael Seibel

Using Cryptocurrency in Real Life

Ask HN: Would you pay for a fully encrypted Google Photos alternative?

Ask HN: Is there a Bloomberg terminal for NFTs?

Ask HN: What knowledge is still circulated in spreadsheets?

Ask HN: How to improve focus and reduce distractions?

comments