ResearchAtPlay

Ehm, no! The same prompt does not always lead to the same output.

Have you ever tried to achieve consistently deterministic output from an LLM? I have, and it's not easy.

That means output differs between machines and architectures. Running inference on CPU vs GPU also affects output. Even running the same prompt twice in a row on the same machine can lead to different outputs because a prompt that was partially stored in the kv cache will result in different output than an uncached prompt.

LLM output is very much not deterministic!

No! Write the LAST damn draft yourself!

The technology already dictates that you must write the first draft yourself because AI can only respond to your initial prompt. That initial prompt IS your first draft.

The title's statement (and the argument presented in the rather short article) appears misinformed about the strengths of AI and where those strengths can support an effective writing process that leads to concise, thorough, and pleasant communication with your audience.

Large language models excel at sketching initial outlines, adding new perspectives, highlighting thematic connections, and shaping format, spelling, and grammar. But their tendency to converge towards an average makes those models terrible at selecting precise terminology, avoiding verbosity, and conveying passion through careful iteration.

My advice: Let AI throw truckloads of slop onto your daunting blank page! Read it to spawn your thoughts, then re-write your message from scratch! That's right - do not attempt to salvage the slop. Borrow the inspiration but avoid copying the words. Then re-read and re-fine. And then again. And again.

And much like the principles of good design have taught us, your writing task is complete when no word can be removed and no term could be replaced to more accurately express your intent.

(Disclaimer: This comment was entirely written without AI.)

This article discusses the DGX Spark GB10 GPU architecture from a hardware engineering perspective. The authors explain the trade-offs between datacenter Blackwell and consumer Blackwell chips, list key hardware features that evolved between GPU generations, and highlight some of the challenges that have resulted on the software side with incomplete support from Triton, Flashinfer, and various kernel incompatibilities.

This is great! I've forwarded the site to my wife.

Would you mind sharing how you trained the model to produce the vectors? Are you using a vision transformer under the hood with contrastive training against price, product category, etc.?

EDIT: I see that the training script is included in the repo and you are using a CNN. Inspiring work!

Makes sense. My main takeaway from the ColPali paper (and your comments) is that ColPali works best for document RAG, whereas vision model embeddings are best used for image similarity search or sentiment analysis. So to answer my own question: The best model to use depends on the application.

Thanks for the link to the ColPali implementation - interesting! I am specifically interested in evaluation benchmarks for different image embedding models.

I see the ColiVara-Eval repo in your link. If I understand correctly, ColQwen2 is the current leader followed closely by ColPali when applying those models for RAG with documents.

But how do those models compare to each other and to the llama3.2-vision embeddings when applied to, for example, sentiment analysis for photos? Do benchmarks like that exist?

This article fundamentally misunderstands the role and purpose of bureaucracy.

Bureaucracy is tool to manage large, complex, and heterogeneous systems. Ideally, efficient and effective bureaucracy goes unnoticed. Why can I plug my laptop into the power outlet anywhere in Miami or in Vancouver and it just works? Why can I drive on the right side of the road from Toronto to San Diego and be reasonably sure that everyone else will drive on the right side as well?

Because humans have self-organized into a multitude of governments, standards organizations, and corporations that all align to produce the same shape of power plug and teach compatible rules-of-the-road across vast geographical distances and unrelated communities. Without bureaucracy, we humans would not be capable of building a global society.

Pointing to broken, ineffective, and inefficient processes to scapegoat “the bureaucrat” reveals an ignorance of the underlying mechanisms that make human society function.

EDIT: To those of you downvoting this comment, please let me elaborate.

I am tired of the trope of the lazy bureaucrat because I refuse to believe that inefficient government and corporations are inevitable.

I do believe that we must strive for efficient and effective government to improve our society because the potential benefits are immense.

Those improvements must be driven by competent and qualified leaders who understand and foster the advantages that result from collaboration, communication, and making choices that benefit society as whole.

A failure of bureaucracy is a failure of leadership!

The purpose of this tool is testing if a domain name system follows (or does not follow) the correct specifications:

IBDNS fills a gap in the universe of DNS test tools by offering the possibility of deviating intentionally and on demand from the DNS specifications, and thus simulating incorrect behaviour of authoritative name servers.

Voluntary carbon markets typically trade in both avoidance and removal (i.e. sequestration) credits. Since this site is called Carbon Dioxide Removal I would assume listed trades only cover sequestration, and my cursory review of the listed removal methods appears to confirm that only sequestered carbon trading is listed (but the methods section does not state this explicitly).

Regarding "is it paying for stuff that would have happened anyway, or is it somehow net removal?": One of the requirements for generating carbon credits is additionality, i.e. a project should only receive carbon credits if it were not viable without the revenue from those credits. But as you point out, determining additionality is rather difficult and often fuzzy.