@dylan@journa.host avatar

dylan

@dylan@journa.host

Machine learning / AI Initiatives at The New York Times.

Coding new tools for journalists and the public.

Past at The Washington Post, DocumentCloud, Stanford Journalism, Google AI. 🏃🏻 🎹

This profile is from a federated server and may be incomplete. Browse more on the original instance.

dylan, to random
@dylan@journa.host avatar

Some news: today is my first day as a senior machine learning engineer at The New York Times!

I'll be working on the new AI Initiatives team in the newsroom to prototype tools, shape standards, and aid reporting. Can't wait to get started!

I will miss my colleagues at The Washington Post and am thankful to the news eng / elections team for supporting my development and encouraging open source projects over the past three years. Here's to finding future avenues for collaboration!

dylan,
@dylan@journa.host avatar

@zubakskees Thanks, Chris!

dylan,
@dylan@journa.host avatar

@chrisamico Thanks! We shall see!

dylan, to opensource
@dylan@journa.host avatar

I'm excited to announce Semantra: an open source multi-tool for semantic search 🎉 https://github.com/freedmand/semantra

  • Launch a local search engine over text and PDF files
  • Search by concepts/meaning
  • Refine results via tagging and adding/subtracting queries

Try it out now 🚀📚🔍

video/mp4

dylan,
@dylan@journa.host avatar

@philippsteinkrueger It looks like the problem’s on Huggingface’s end. Their platform hosts the models Semantra uses.

I would try again throughout the day — it should come back up soon. Once Semantra has downloaded the model from Huggingface once, it will work entirely offline.

https://status.huggingface.co

dylan,
@dylan@journa.host avatar

@philippsteinkrueger Looks like GitHub’s having issues this morning, too. Could be related. Thanks for reporting!

dylan, to ai
@dylan@journa.host avatar

I'm working on an open source semantic search command-line tool — coming soon! 🔎

It analyzes text files you specify and launches a local web server to search them semantically — based on meaning and not exact word matches.

dylan,
@dylan@journa.host avatar

@rer Hi! Thanks for reporting the issue. I haven't run into that one, but from searching on the web installing gcc-c++ may be the fix here.

Can you try the following: https://stackoverflow.com/a/21154624

I'm not familiar with Fedora so I'm not sure if the instructions are relevant to your OS.

If you feel comfortable, you may also wish to create an issue on the GitHub repo as others may have experienced and solved this problem, too: https://github.com/freedmand/semantra/issues

  • All
  • Subscribed
  • Moderated
  • Favorites
  • •
  • megavids
  • thenastyranch
  • rosin
  • GTA5RPClips
  • osvaldo12
  • love
  • Youngstown
  • slotface
  • khanakhh
  • everett
  • kavyap
  • mdbf
  • DreamBathrooms
  • ngwrru68w68
  • provamag3
  • magazineikmin
  • InstantRegret
  • normalnudes
  • tacticalgear
  • cubers
  • ethstaker
  • modclub
  • cisconetworking
  • Durango
  • anitta
  • Leos
  • tester
  • JUstTest
  • All magazines
    •