Hacker News

Article URL: https://www.core64.io

Comments URL: https://news.ycombinator.com/item?id=41567240

Points: 1

# Comments: 0

Article URL: https://www.smithsonianmag.com/science-nature/tens-of-thousands-of-tiny-tags-are-revealing-the-secret-lives-of-birds-180985022/

Comments URL: https://news.ycombinator.com/item?id=41567215

Points: 2

# Comments: 0

Article URL: https://www.youtube.com/watch?v=p-RDpKFQVhI

Comments URL: https://news.ycombinator.com/item?id=41567196

Points: 1

# Comments: 0

Article URL: https://www.youtube.com/watch?v=xepC3-Ia9ho

Comments URL: https://news.ycombinator.com/item?id=41567195

Points: 1

# Comments: 0

Hey HN! I'm Caleb, one of the contributors to Opik, a new open source framework for LLM evaluations.

Over the last few months, my colleagues and I have been working on a project to solve what we see as the most painful parts of writing evals for an LLM application. For this initial release, we've focused on a few core features that we think are the most essential:

- Simplifying the implementation of more complex LLM-based evaluation metrics, like Hallucination and Moderation.

- Enabling step-by-step tracking, such that you can test and debug each individual component of your LLM application, even in more complex multi-agent architectures.

- Exposing an API for "model unit tests" (built on Pytest), to allow you to run evals as part of your CI/CD pipelines

- Providing an easy UI for scoring, annotating, and versioning your logged LLM data, for further evaluation or training.

It's often hard to feel like you can trust an LLM application in production, not just because of the stochastic nature of the model, but because of the opaqueness of the application itself. Our belief is that with better tooling for evaluations, we can meaningfully improve this situation, and unlock a new wave of LLM applications.

You can run Opik locally, or with a free API key via our cloud platform. You can use it with any model server or hosted model, but we currently have a built-in integration with the OpenAI Python library, which means it automatically works not just with OpenAI models, but with any model served via a compatible model server (ollama, vLLM, etc). Opik also currently has out-of-the-box integrations with LangChain, LlamaIndex, Ragas, and a few other popular tools.

This is our initial release of Opik, so if you have any feedback or questions, I'd love to hear them!

Comments URL: https://news.ycombinator.com/item?id=41567192

Points: 2

# Comments: 0

Article URL: https://jacobbartlett.substack.com/p/compiler-cocaine-the-swift-method

Comments URL: https://news.ycombinator.com/item?id=41567178

Points: 1

# Comments: 0

Article URL: https://www.tax-the-rich.eu

Comments URL: https://news.ycombinator.com/item?id=41567173

Points: 2

# Comments: 0

Article URL: https://www.theregister.com/2024/09/17/ai_sp_500_q2/

Comments URL: https://news.ycombinator.com/item?id=41567169

Points: 1

# Comments: 0

Article URL: https://www.youtube.com/watch?v=4pLQxz-EeQ8

Comments URL: https://news.ycombinator.com/item?id=41567163

Points: 1

# Comments: 0

Article URL: https://read.perspectiveship.com/p/correlation-vs-causation

Comments URL: https://news.ycombinator.com/item?id=41567150

Points: 1

# Comments: 0

Article URL: https://www.restoreamericadream.org/

Comments URL: https://news.ycombinator.com/item?id=41567143

Points: 1

# Comments: 1

Article URL: https://www.youtube.com/watch?v=b_sKQ5Gk4EM

Comments URL: https://news.ycombinator.com/item?id=41567140

Points: 1

# Comments: 0

Article URL: https://www.arxiv.org/abs/2409.06750

Comments URL: https://news.ycombinator.com/item?id=41567138

Points: 1

# Comments: 0

Article URL: https://home.cern/news/press-release/physics/cms-experiment-cern-weighs-w-boson-mass

Comments URL: https://news.ycombinator.com/item?id=41567129

Points: 1

# Comments: 0

I'm in the market for an engineering job over the past two months but I'm really struggling at finding one. Basically, my story is:

- Full Stack with 12+ years of experience, good generalist/architect with a some strong points.

- Working remotely in EU timezone.

- Got a nice CV with big names and projects I significantly contributed on.

- Last full time job was 1.5 years ago but I have done plenty of one-off client and personal projects in the meantime I can show off.

I only apply to positions that are fully remote in my timezone and where the profile is at least an 80% match or more. I often tick multiple of the "nice to have" boxes. I put quite some effort in my applications, writing cover letters or filling all boxes in the form with relevant and personalized information, Despite that, most companies reject me right away.

When I make it further, I usually pass coding tests with flying colors. It does happen that I bomb the technical questions due to stress, I can't find the right words to explain how I would solve something but in code it's not an issue. The non-technical calls usually go very well, I'm a likable guy and can hold a good conversation.

So far, I got zero offers. I'm even ready to take a 50% pay cut compared to my previous position. Is the market really that bad or is my profile just undesirable? Or am I doing something wrong? I'm really starting to feel desperate. Any advice or ideas would greatly help.

Ps: This is not self promotion (thus the throwaway/anonymous account), not asking for a job just advice.

Comments URL: https://news.ycombinator.com/item?id=41567121

Points: 1

# Comments: 0

Article URL: https://dev.to/mustapha/why-html-has-both-b-i-and-strong-em-4k5c

Comments URL: https://news.ycombinator.com/item?id=41567116

Points: 1

# Comments: 0

Article URL: https://github.com/mazzzystar/tinymind

Comments URL: https://news.ycombinator.com/item?id=41567103

Points: 1

# Comments: 0

Article URL: https://redmonk.com/sogrady/2024/09/12/language-rankings-6-24/

Comments URL: https://news.ycombinator.com/item?id=41567090

Points: 1

# Comments: 0

Article URL: https://testrigor.com/blog/top-10-owasp-for-llms-how-to-test/

Comments URL: https://news.ycombinator.com/item?id=41566840

Points: 1

# Comments: 0

Reposting this because of recent Ask thread interest in a similar solution: https://news.ycombinator.com/item?id=41519046

Feel free to contribute sound pieces and new rules!

Comments URL: https://news.ycombinator.com/item?id=41566833

Points: 1

# Comments: 0