I'm only here because @simonwillison.net posted about this on elon's plaything.

Built on top of the powerful open access API services of the NIH:

- ClinicalTrials.gov

- MyVariant.info

- PubMed / Pubtator3
www.ncbi.nlm.nih.gov/research/pub...

Introduction to BioMCP YouTube video by GenomOncology

Short video on YouTube:
www.youtube.com/watch?v=bKxO...

GitHub - genomoncology/biomcp: BioMCP: Biomedical Model Context Protocol BioMCP: Biomedical Model Context Protocol. Contribute to genomoncology/biomcp development by creating an account on GitHub.

Github Repo (MIT License):
github.com/genomoncolog...

Proud to announce BioMCP, an open source Model Context Protocol (MCP) server for biomedical research AI assistants and agents. BioMCP searches and retrieves clinical trials, PubMed articles and genomic variants to provide up-to-date and relevant context to an LLM.

slick!

Listening now... came here to say congrats. :)

I did finish it and listened to your podcast with @mkennedy.codes

Good stuff. Subscribed on overcast.

Great article this morning. Got to the blog scroll link and… now I am here.

I hope I don’t get distracted too much longer. I want to finish it.

Your line colors are messing with my mind.

You can’t for-loop taste

Just everything else with AI, you can get good results with low effort.

Then you can grind and keep eeking out gains.

This has add’l benefits:
- improvement on that task
- greater vision of what else you can do
- higher expectations on what good results are
- better first drafts the next time.

Just everything else with AI, you can get good results with low effort.

Then you can grind and keep eeking out gains.

This has add’l benefits:
- improvement on that task
- greater vision of what else you can do
- higher expectations on what good results are
- better first drafts the next time.

How are they going to get the sun to shine like that in winter?

1. No
2. NaN

PDF version

arxiv.org/pdf/2408.02442

Let Me Speak Freely? A Study on the Impact of Format Restrictions on Performance of Large Language Models Structured generation, the process of producing content in standardized formats like JSON and XML, is widely utilized in real-world applications to extract key output information from large language m...

Perplexity did find me this quote:

“Upon inspection, we found that 100% of GPT 3.5 Turbo JSON-mode responses placed the "answer" key before the "reason" key, resulting in zero-shot direct answering instead of zero-shot chain-of-thought reasoning.”

ar5iv.org/html/2408.02...

Any research on the impact of JSON key sort order on generating structured outputs?

For instance, I do something like this:

- analyze
- draft
- evaluate
- final

And then provide exemplars with errors to show self correction.

But I haven’t done extensive testing. Just seems like a good idea.

Congrats!

Ugh. Sorry to hear this.

Among Us lol.

That's my favorite fun fact about SQLite. Seems to be a competitive advantage for them securing contracts from large organizations.

Which, good on them, I think it's a more than fair way to do OSS.

That’d be sweet. Thank Claude for me.

Bunny CDN still treating you alright?

Nice looking script.

You are right bytes not tokens.

Git ingest Replace 'hub' with 'ingest' in any Github Url for a prompt-friendly text

Git ingest:
gitingest.com

Chat with any open source repo easily. Gitingest (free online tool) turns any GitHub repository into a single markdown file for pasting. Claude artifacts makes this 300k token output pretty easy to work with.

Makes sense. Thanks for the clarification.

I was wondering if it was a copyright thing which didn’t make much sense given the technology.

Great thoughts.

AT protocol is interesting for the same reason podcasts are interesting. Love the open web.

Can you explain the legalities of why you can’t have a play button for some podcasts that have a public mp3 url?