haensi

Reminds me of the question “why do good people go bad?” What are invisible forces? What is good? What is evil? Physicists, philosophers and theologians alike think about those questions.

Do those questions need a foundation on which they stand to be answered? What is that foundation (are there relative foundations or are they by definition absolute?)?. Is there a moral standard that those handful of companies share? Similar to “success factors”, are there “success ethics” in your perspective?

What would be the elements of success ethics that others can learn from?

What kind of Christian books do you read?Jonathan Edwards, John Bunyan, J.C. Ryle, C.H. Spurgeon?

I’m a Christian as well and spent a day in Oxford earlier this year. After spending some time at Magdalen College, I bought every book I could by C.S. Lewis and just finished Letters to Malcolm (on prayer) today.

His refreshingly honest take is very relatable, humorous and encouraging.

I can highly recommend it if you’re interested in prayer life (and how to use powerful formulations in letters)

Weights & Biases if they are serious and need performance and scale.

Thanks for sharing this, I was not aware of it and I’m currently in the process of learning Hebrew, dealing with the intersection of (Jewish and Christian) culture and technology.

One example is a GPT version [1] fine tuned on texts of Sefaria [2].

The initiator was in direct contact with Sam Altman to kickstart it. (Personal communication).

He talks about this publicly [3]

[1] https://github.com/Sefaria/AppliedAI [2]: https://www.sefaria.org/texts [3]: https://m.youtube.com/watch?v=tZkJl2fk0rc

There’s another thread from October 2022 on that topic.

https://news.ycombinator.com/item?id=33047634

What makes DVC especially useful for MLOps? Aren’t MLFlow or W&B solving that in a way that’s open source (the former) or just increases the speed and scale massively ( the latter)?

Disclaimer: I work at W&B.

Their CEO talks about this in the gradient dissent podcast [1]

[1] https://m.youtube.com/watch?v=qNXebAQ6igs

Very interesting to see an LLM with weights and the code base. They also talk about tokenizer fertility in the HF model card [1]

[1] https://huggingface.co/Aleph-Alpha/Pharia-1-LLM-7B-control

Thanks a lot I will check those out. I love used books, I already have found so many treasures that were unknown to me before.

You made my day with woulda shoulda cuda.

I’m going to watch finding NeMo now

You mean something like this?

https://targum.video/

Thanks for this 101 article! The entire LLMOps field is developing so fast and is being defined as we speak.

Somehow, this time feels to me like the early days of computer science, when Don Knuth was barely known and a Turing award was only known to Turing award winners. I met Don Knuth in Palo Alto in March and we talked about LLMs. His take: „Vint Cerf told me he was underwhelmed when he asked the LLM to write a biography on Vinton Cerf.“

There are also tools being built and released for Prompt engineering [1]. Full transparency: I work at W&B

LangChain and other connecting elements will vastly increase the usability and combinations of different tools.

[1] https://wandb.ai/wandb/wb-announcements/reports/Introducing-...

Do you mean something like Whisper.cpp? [0] See the demo there.

[0] https://github.com/ggerganov/whisper.cpp#whispercpp

Have you tested Weights & Biases Artifacts[1]?

It comes with a smart versioning approach, checks the Δ based on the checksum and has a feature to visualize the lineage.

You can also use your existing object store and link it for very large / sensitive data.[2]

Disclaimer: I work at W&B.

[1] https://docs.wandb.ai/guides/data-and-model-versioning/model... [2]: https://docs.wandb.ai/guides/artifacts/track-external-files#...

Don Knuth further elaborates on this in his great book Things [0], [2]:

The truth in fact is that C. P. Snow got it wrong by at least an order of magnitude — there are many more than two cultures. I think a lot of you know the Apple Macintosh ads telling us to “think different,” but people already do. From my own corner of the academic world, I know for example that physicists think different from mathematicians; mathematicians who do algebra think different from mathematicians who do geometry; both kinds of mathematicians think different from computer scientists who work on algorithms; and so on and so forth. People often decry this lack of unity in the knowledge of the world, but let’s face it: People are different. Vive la différence.

Fun fact: PG mentions the two cultures while writing about Knuth [1]

[0] http://web.stanford.edu/group/cslipublications/cslipublicati...

[1] http://www.paulgraham.com/knuth.html?viewfullsite=1

[2] https://en.wikipedia.org/wiki/Things_a_Computer_Scientist_Ra...

I currently teach computer science at a local high school. Topics range from algorithms and data structures to AI and societal impact.

I do it to encourage young people to use software to make a change in their and other’s lives.

Currently making $500 with 90min/week effort. I already got the syllabus material ready so I do not necessarily have to invest time here.

Right now they’re writing an exam.

* howdoi: stackoverflow from the shell: https://github.com/gleitz/howdoi, don't leave you terminal while programming