Dylan Freedman @dylfreed Twitter profile

Pinned Tweet

Dylan Freedman

1 year

I'm excited to announce Semantra: an open source multi-tool for semantic search 🎉 - 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 🚀📚🔍

35

93

601

Last Seen Profiles

@435_yo

@marcusboakye

@LuckyJack213

@Gypsophila0808

@mohamed24790162

@eleargo

@Miya2003HYN

@IPSAthletics

@bbcdavideades

@CoachFerber

@Beckyrichards02

@Nawaal722037494

@Ai_ven_o_gol

@SaneTrader_Ro

@otaki3634

@TWXNTX_1

@shinto_s

@SPAMisgood7

@timesbridge

@ZortsSports

@ZeroTopey

@sv_mervat1

@starboard_light

@ReactEurope

@ESPN_FDJ

@hharussya

@ComradeKat64

@Victor62201135

@monicalimco

@RichSwin

@GuyBedaine

@listi39616

@Martins_458

@dakeoogiya

@toine_lec

@shijieswife

Dylan Freedman

@dylfreed

3 months

New open source OCR model just dropped! This one by Microsoft features the best text recognition I've seen in any open model and performs admirably on handwriting. It also handles a diverse range of vision tasks. You can play with it here:

Brandon Roberts

@bxroberts

2 years

This is incredible. IT CAN DO HANDWRITING RECOGNITION. I've been testing on some of the shakiest handwritten public records I have and I'm getting good results. This is a big deal for lots of journalism workflows. See this example 👇

4

22

157

40

503

3K

Dylan Freedman

@dylfreed

28 days

The new Qwen2-VL-7B Instruct model gets *100%* accuracy extracting text from this handwritten document. This is the first open weights model (Apache 2.0) that I've seen OCR this accurately. (Thank you @fdaudens for the tip!)

Dylan Freedman

@dylfreed

1 month

Microsoft's new open source Phi 3.5 vision model is really good at OCR/text extraction — even on handwriting! You can prompt it to extract tabular data as well. It's permissively licensed (MIT). Play around with it here:

16

193

1K

35

249

2K

Dylan Freedman

@dylfreed

1 month

Microsoft's new open source Phi 3.5 vision model is really good at OCR/text extraction — even on handwriting! You can prompt it to extract tabular data as well. It's permissively licensed (MIT). Play around with it here:

Dylan Freedman

@dylfreed

3 months

New open source OCR model just dropped! This one by Microsoft features the best text recognition I've seen in any open model and performs admirably on handwriting. It also handles a diverse range of vision tasks. You can play with it here:

40

503

3K

16

193

1K

Dylan Freedman

@dylfreed

11 months

Prototyping a real-time AI writing tool to show how large language models are essentially probability engines. (thanks to @ggerganov 's llama.cpp for enabling this to run rapidly on an 8GB RAM MacBook Air)

15

39

394

Dylan Freedman

@dylfreed

6 months

Some news: today is my first day as a senior machine learning engineer at @nytimes ! 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!

17

7

182

Dylan Freedman

@dylfreed

5 years

I could not find a zoomable, explorable map of COVID-19 cases in the US, so I rolled my own: Deeply indebted to @USAFacts for the data along with the zippy @sveltejs and #deckgl JS frameworks.

16

85

168

Dylan Freedman

@dylfreed

2 years

Introducing Textra, a free + open source OCR tool I created using Apple's new Vision API 🖼️✨📄 Textra runs on the command line and quickly/accurately converts PDF and image files to text (requires Mac OS 13+). Check it out! #opensource

Dylan Freedman

@dylfreed

2 years

Apple's Live Text OCR is amazingly high quality and runs entirely offline. I spun up a quick demo of it transcribing a PDF of the Mueller Report page by page and outputting the transcript as it goes:

1

24

6

35

150

Dylan Freedman

@dylfreed

2 years

Update: Crosswalker is now open source! It's a general purpose tool for joining columns of text data that don't match perfectly. 🕸️ runs in the browser 🔒 keeps your data entirely local 😌 auto-saves your progress

Dylan Freedman

@dylfreed

2 years

In the works @WapoEngineering : a general text matching tool to help join columns of data when the names don't exactly match. We're using it for election precinct matching🗳️

9

11

104

3

40

134

Dylan Freedman

@dylfreed

1 year

@jeremybowers We'll be telling our grandchildren how clean the data streams used to be

Dylan Freedman

@dylfreed

2 years

AI-generated content is the new microplastics

0

11

48

0

12

112

Dylan Freedman

@dylfreed

2 years

In the works @WapoEngineering : a general text matching tool to help join columns of data when the names don't exactly match. We're using it for election precinct matching🗳️

9

11

104

Dylan Freedman

@dylfreed

3 years

I'm really excited to open source the campaign finance toolset I've been working on with @WapoEngineering recently: a speedy C framework and CLI to transform raw FEC filings into CSV files! ⚡️

GitHub - washingtonpost/FastFEC: An extremely fast FEC filing parser written in C

An extremely fast FEC filing parser written in C. Contribute to washingtonpost/FastFEC development by creating an account on GitHub.

github.com

3

13

94

Dylan Freedman

@dylfreed

7 years

An interactive computational essay on sound using @observablehq notebooks! Learn about waveforms and musical pitch by visualizing and listening to sound functions.

Sounds

In the first part of this primer, we cover classic oscillator functions — or repeating sonic patterns — including sine waves, sawtooth waves, square waves, and triangle waves. We also discuss the...

observablehq.com

3

16

71

Dylan Freedman

@dylfreed

4 years

Over the past ~3 years, I've been working hard on a complete rewrite of with @muckrock — a platform that lets you analyze, annotate, and publish document collections. Today, I'm proud to announce we publicly launched the new site and open sourced the code!

4

21

61

Dylan Freedman

@dylfreed

2 years

AI-generated content is the new microplastics

0

11

48

Dylan Freedman

@dylfreed

2 years

🎉 Some belated personal news: I'm leading backend/platforms engineering for elections @washingtonpost under the direction of @anthonyjpesce and @jeremybowers Could not ask for better colleagues to work with!

Washington Post PR

@WashPostPR

2 years

The Washington Post dramatically expands Elections Engineering team, bolstering 2022 coverage

1

14

4

1

38

Dylan Freedman

@dylfreed

3 years

Working on a side project to debug and visualize AWS step functions locally, and it's going well so far! (This should make it easier to iterate, flow data, and see errors without having to deploy to AWS each time)

3

2

36

Dylan Freedman

@dylfreed

3 years

✨Career update: today is my last day at @documentcloud . The past three years have been thrilling! I'm so thankful for the opportunity to work and grow with @muckrock and pilot incredible tech. In mid-July, I'll be joining @washingtonpost as a senior full-stack newsroom engineer!

4

1

36

Dylan Freedman

@dylfreed

3 years

. @lennybronner and I just presented on FastFEC and the @WapoEngineering FEC pipeline at #NICAR22 ! Check out the project website to see our demo and presentation slides:

0

9

35

Dylan Freedman

@dylfreed

1 month

Prompts I used: "OCR this image and provide just the output text. Format it all as plain text" (for the handwriting example) "OCR this image and provide just the output text. Format it all as markdown" (for the table extraction example)

1

2

34

Dylan Freedman

@dylfreed

2 years

Update: got it done

Dylan Freedman

@dylfreed

2 years

Running 100 miles today

5

1

16

9

0

32

Dylan Freedman

@dylfreed

3 months

@sterenas Yes! Check out the instructions here: I also shared some code I used to get it to run on CPU here:

microsoft/Florence-2-large · Hugging Face

huggingface.co

Dylan Freedman

@dylfreed

3 months

@mcnatch I was able to get it running on the CPU following advice here (the import structure without patching requires running it on GPU/CUDA):

3

0

23

1

3

31

Dylan Freedman

@dylfreed

3 years

Update! FastFEC is now installable via #homebrew on Mac/Linux: brew install fastfec

Dylan Freedman

@dylfreed

3 years

I'm really excited to open source the campaign finance toolset I've been working on with @WapoEngineering recently: a speedy C framework and CLI to transform raw FEC filings into CSV files! ⚡️

3

13

94

1

4

29

Dylan Freedman

@dylfreed

2 years

A new version of Textra is out! Textra is a command-line tool to extract text from images, PDFs — and now audio. It runs on Mac OS 13+ and uses Apple's APIs for fast, on-device text extraction. #opensource

1

6

25

Dylan Freedman

@dylfreed

3 months

@snappercayt Interesting. The captioning/OCR seems to work better on smaller images with consistent text sizes. It could be useful to chain this model on top of another layout/bounding box model. Also this isn’t my model — it’s Microsoft’s:

microsoft/Florence-2-large · Hugging Face

huggingface.co

1

4

27

Dylan Freedman

@dylfreed

2 years

Apple's Live Text OCR is amazingly high quality and runs entirely offline. I spun up a quick demo of it transcribing a PDF of the Mueller Report page by page and outputting the transcript as it goes:

1

24

Dylan Freedman

@dylfreed

3 months

@mcnatch I was able to get it running on the CPU following advice here (the import structure without patching requires running it on GPU/CUDA):

3

0

23

Dylan Freedman

@dylfreed

3 months

@simonw I was thinking you could get good results extracting a table's layout using existing models / algorithms (some of which are not even ML-based!) and then feeding in image subsections to this kind of high quality OCR model

2

1

21

Dylan Freedman

@dylfreed

1 year

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. #ai #nlp #semanticsearch

2

0

19

Dylan Freedman

@dylfreed

1 year

🚨🗳️ Interested in working on elections at The Washington Post? Our Election Platforms team is hiring! We build data pipelines, results page infrastructure, admin interfaces, and many special projects — and work with with incredibly talented individuals:

2

7

19

Dylan Freedman

@dylfreed

3 months

Life update!

2

0

17

Dylan Freedman

@dylfreed

1 year

Working on a new feature in Semantra (coming soon!): the ability to add and subtract semantic queries 🔥 It's fun to iterate with! Here's a section I found in the Mueller Report about caviar by searching for lavish bribery and positively/negatively tagging some search results.

Dylan Freedman

@dylfreed

1 year

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. #ai #nlp #semanticsearch

2

0

19

2

3

17

Dylan Freedman

@dylfreed

1 year

A very early in-progress demo of Semantra running entirely in-browser. No backend thanks to transformers.js! The possibilities include being able to export document collections as static, hostable websites users can search without installing anything.

Dylan Freedman

@dylfreed

1 year

I'm excited to announce Semantra: an open source multi-tool for semantic search 🎉 - 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 🚀📚🔍

35

93

601

2

4

17

Dylan Freedman

@dylfreed

2 years

Running 100 miles today

5

1

16

Dylan Freedman

@dylfreed

2 years

@morisy @goodside I think the most captivating thing about this AI is that trying to fool it has turned into a game, with particularly hilarious and witty bypass mechanisms. It's the challenge of getting into the prompt makers' minds and subverting their defensive plays.

1

15

Dylan Freedman

@dylfreed

2 years

In the studio with Jeremy. The time has come!

Jeremy Bowers

@jeremybowers

2 years

IT IS ALMOST TIME

8

0

77

1

0

15

Dylan Freedman

@dylfreed

1 year

I made a simple web application to study for the 100 question #USCIS US Citizenship Civics exam. It allows you to click/tap on questions to reveal answers and has a button to shuffle the order of the questions. Try it out here:

2

14

Dylan Freedman

@dylfreed

2 years

Very cool, thank you for sharing all this data! I put together a quick @observablehq notebook to explore the homes on an interactive map

Single-family homes owned by large corporate landlords in North Carolina

An interactive map to view single-family homes in North Carolina owned by large corporate landlords (only those that own at least 100 properties are shown). Data from Security for Sale, an analysis...

observablehq.com

Tyler Dukes

@mtdukes

2 years

We’re releasing all of our data on all 40,000+ properties identified using @NCOneMap data, along with our subsidiary lookup. We’re hoping it will help the public, researchers & policymakers understand the scope of corporate homeownership #securityforsale

1

16

55

0

5

14

Dylan Freedman

@dylfreed

7 months

Excited to be at #NICAR24 in Baltimore this year! If you want to learn more about campaign finance analysis, come check out @ccemorse 's and my free session (offered Thursday / Friday).

2

0

14

Dylan Freedman

@dylfreed

20 days

Hey, look, the handwritten document @bxroberts shared to benchmark an OCR tool I wrote 21 months ago (and subsequently I used to eval visual language models) made it into @MistralAI ’s demo deck

swyx @ DevDay!

@swyx

20 days

@GuillaumeLample @ArtificialAnlys @dchaplot @altryne @imhaotian Pixtral absolutely SLAYS at OCR hot damn

2

9

82

1

0

13

Dylan Freedman

@dylfreed

3 years

Very excited to launch a new flagship @documentcloud feature: selectable text! The viewer allows text to be selected, copied, and searched. The processing pipeline does OCR, extracts positional text, and grafts it back in to create a searchable/selectable PDF (extremely quickly).

1

3

13

Dylan Freedman

@dylfreed

8 months

Currently tinkering on a tool to interpret and understand ML/AI models. It operates on @PyTorch models and launches an interactive frontend to display the model architecture, run the models in real-time, and add visualization blocks.

1

10

Dylan Freedman

@dylfreed

3 years

@WapoEngineering It's still very early stages, so look out for some fun next steps like making it a Homebrew and Python package along with more rigorous testing and documentation! But the word got out early

Jeremy Bowers

@jeremybowers

3 years

👀

3

2

43

1

2

11

Dylan Freedman

@dylfreed

3 months

This is a great example of how large language models work probabilistically. Once ChatGPT outputs a few states in alphabetical order, the probability that the next one will be "Connecticut" is high — even though it contains no 'a' — because it has been trained on data like this.

Ed Zitron

@edzitron

3 months

Sounds great ChatGPT thanks again for being so smart

67

93

2K

0

3

10

Dylan Freedman

@dylfreed

28 days

@k3ntosan @fdaudens Seems to work well on tables. Here I prompted it to extract in Markdown format:

1

0

10

Dylan Freedman

@dylfreed

1 year

Working on a feature to search PDF documents semantically

Dylan Freedman

@dylfreed

1 year

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. #ai #nlp #semanticsearch

2

0

19

0

1

10

Dylan Freedman

@dylfreed

5 years

For the past year and a half we've been working on a new, faster, redesigned version of DocumentCloud. I'm excited to publicly demo the new beta tomorrow morning at #NICAR2020

DocumentCloud

@documentcloud

5 years

Hey #NICAR20 ! Come get a first look at the new @DocumentCloud beta and a chance to get early access: Join @dylfreed ’s session Friday morning at 9am to see how fast we’ve made it:

0

7

4

2

10

Dylan Freedman

@dylfreed

1 year

I wrote documentation for Semantra in hopes it will be serviceable. Please let me know if you have any feedback, encounter any issues, or have any suggestions/ideas! Repo: Tutorial: Guides:

6

1

10

Dylan Freedman

@dylfreed

1 year

Semantra is built for those seeking needles in haystacks: journalists, researchers, students, and more. I've found it useful personally across a wide range of content, including books, reports, speeches, and government documents. Tutorial:

1

9

Dylan Freedman

@dylfreed

2 years

Looking forward to presenting at my first @SRCCON with @whatuphails ! We'll be talking about breaking silos by open sourcing your newsroom's internal tools — Friday at 11:30am ET. Themes include: community building, technical design, org buy-in, and more. See you there! #SRCCON22

1

2

9

Dylan Freedman

@dylfreed

4 years

For those familiar with the brilliant 10+ year old legacy platform, this is a from-the-ground-up revamp for the 2020s. We're talking modern, mobile-friendly web app/embeds, robust serverless processing that crunches documents in < 1 minute, and advanced search/OCR/entity features

1

9

Dylan Freedman

@dylfreed

8 months

✨ Introducing Interpogate A tool to visualize and inspect @PyTorch model architectures. It works in Jupyter notebooks/Google Colab, operates on a diverse range of models, and has a convenient API to attach hooks to observe model behavior in realtime.

Dylan Freedman

@dylfreed

8 months

Currently tinkering on a tool to interpret and understand ML/AI models. It operates on @PyTorch models and launches an interactive frontend to display the model architecture, run the models in real-time, and add visualization blocks.

1

10

0

7

Dylan Freedman

@dylfreed

1 year

Friends, the Election Platform team at The Washington Post is hiring a senior full-stack engineer! We're working on internal tools and architecture to power elections coverage that reaches millions of readers. Join us:

1

9

Dylan Freedman

@dylfreed

3 years

Also of note, FastFEC utilizes @ziglang for its C build system, which provides an extremely smooth cross-platform compilation experience. I look forward to using Zig (and admiring mascot Ziggy) for more things going forward!

0

9

Dylan Freedman

@dylfreed

2 years

@simonw I recommend checking out the open-source tool k2pdfopt, which does an amazing job at reflowing PDFs

1

0

8

Dylan Freedman

@dylfreed

2 years

Source code and documentation:

GitHub - washingtonpost/crosswalker: A general purpose tool for text-based crosswalking

A general purpose tool for text-based crosswalking - washingtonpost/crosswalker

github.com

1

8

Dylan Freedman

@dylfreed

11 months

@ggerganov Thank you! It does a good job catching typos (and awkward phrasings, omitting needed words in sentences, etc.). It varies in effectiveness based on where the tokenization of a split word falls. Re: source code, will look deeper! It catches typos here too/has decent suggestions

1

0

8

Dylan Freedman

@dylfreed

4 years

Working on a project of this scale has been daunting/ thrilling. I'm incredibly thankful for the leadership and vision from folks like @morisy , Mitch, @pilhofer , boardmembers, and @documentcloud originals @knowtheory + @jashkenas + others. Excited to continue iterating from here!

0

8

Dylan Freedman

@dylfreed

2 years

Excited to have contributed to @iarnsdorf 's must-read piece. Thanks @anu_narayan for all the help analyzing Cawthorn's campaign expenses! #fec

The Washington Post

@washingtonpost

2 years

Rep. Madison Cawthorn (R-N.C.) picked a fight with top GOP leaders in his state. They gave it to him.

34

46

205

0

3

6

Dylan Freedman

@dylfreed

5 years

Giving my first webinar today on the new @DocumentCloud beta! The revamped doc platform is fine-tuned for breaking news with the fastest PDF processing out there. 🏎️🏎️🏎️ Join me on Zoom at 3pm Eastern/12pm Pacific – it's free and open to anyone

0

2

8

Dylan Freedman

@dylfreed

4 months

The newly launched @arcprize challenges A.I. progress, claiming state-of-the-art models are essentially pattern matching at scale and unable to actually acquire new skills. They demonstrate this via a benchmark that's... a surprisingly fun puzzle game

ARC Prize - Play the Game

Easy for humans, hard for AI. Try ARC-AGI.

arcprize.org

1

0

7

Dylan Freedman

@dylfreed

1 year

Here's an example using Semantra on a collection of US inaugural speeches. You can play with this document collection in the tutorial After downloading the documents, analyze them all at once with: ``` semantra us_inaugural_speeches/*.txt ```

1

7

Dylan Freedman

@dylfreed

4 years

We've been in beta for a while so are still improving the homepage and expanding our documentation, but the platform is open and all users/orgs have been migrated over. We're powering millions of documents and 10s of millions of monthly embed page views

1

0

7

Dylan Freedman

@dylfreed

3 years

This was incredibly fun to work on! Thanks to Jon and Sam @ReutersGraphics for instilling the value of adding a dangerous dose of creativity on deadline. (I had an inkling the math would check out but still feel like we got lucky the bracket order didn't break while revolving!)

Jon McClure

@JonRMcClure

3 years

This slick bracket is Dylan's main contribution to the homepage, and it's easily the best part of the app. Lotta trig work went into it, but in keeping with a laconic East London style, we called it The Revolver.

1

0

4

2

0

7

Dylan Freedman

@dylfreed

1 year

@dangerscarf I'm doing a talk that might be more in this spirit for SRCCON in October, with @kat_alo ! Not planning for anything too bellicose, but more like let's be open, talk through problems/solutions from various perspectives, and come up with some ideas together.

SRCCON 2023 — Our Program

A participant-led conference from OpenNews for journalists who want to transform their work, their organizations, and their communities.

2023.srccon.org

1

13

7

Dylan Freedman

@dylfreed

6 months

I will miss my colleagues at @washingtonpost 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!

0

1

7

Dylan Freedman

@dylfreed

2 years

And speaking of Apple's text extraction APIs, here is its speech recognizer running on a 9 hour meeting from the California Coastal Commission. This one also works offline — is anyone using it to freely transcribe interviews?

Dylan Freedman

@dylfreed

2 years

Apple's Live Text OCR is amazingly high quality and runs entirely offline. I spun up a quick demo of it transcribing a PDF of the Mueller Report page by page and outputting the transcript as it goes:

1

24

0

6

Dylan Freedman

@dylfreed

7 years

Thanks to @mfederis and the @PeninsuPress , the story @jackie_botts and I wrote on language access issues for undocumented immigrants after the Sonoma County wildfires is on the homepage of

After the California wildfires, community leaders are trying to rebuild homes — and trust in...

The October wildfires in Northern California are out, but immigrant families are still weary of seeking help from the government.

theworld.org

0

1

7

Dylan Freedman

@dylfreed

1 year

Election Platforms helps architect and build the underlying tools behind elections to make future election nights easier and less stressful for everyone.

1

0

7

Dylan Freedman

@dylfreed

2 years

As someone who's spent a lot of time with Tesseract (the leading free, open source OCR library), I can't help but be excited by the quality/speed improvements Apple's closed source solution seems to offer. Now to think about building an open source command-line tool around it 🤔

2

0

7

Dylan Freedman

@dylfreed

1 year

@Ethan_Connelly Thanks! A key difference is that this can run entirely offline on your own computer for free. Instead of trying to provide a chatbot experience, Semantra provides a human-in-the-loop interface on top of semantic search

0

1

7

Dylan Freedman

@dylfreed

2 years

@lennybronner @WapoEngineering It really excels in that case

0

6

Dylan Freedman

@dylfreed

5 years

Excited to share a virtual reality experience about ocean debris featuring the incredible photography of @plasticpieces . Done in collaboration with my teammates at @StanfordJourn ! Dive into the experience on computer, phone, or VR headset at

1

6

Dylan Freedman

@dylfreed

4 years

An interactive computational essay on how code formatters work! Just in case you're curious or thinking of making a programming language. @observablehq

Pretty Printing

A brief primer on how code auto-formatters work Pretty printing is an art and a science — the distinctly human endeavor of formatting code to look pretty. I recently learned about how pretty printers...

observablehq.com

0

1

6

Dylan Freedman

@dylfreed

4 years

The @DocumentCloud beta is now scrolly AND zoomy! Check out my release notes on architecting a smooth and modern document viewing experience

1

6

Dylan Freedman

@dylfreed

4 months

👀 What's going on in Illinois and Texas? (Request form for Meta's new Chameleon model)

1

0

6

Dylan Freedman

@dylfreed

3 years

@Rich_Harris @jeremybowers To be fair, it’s always shorts season for me

0

6

Dylan Freedman

@dylfreed

9 months

@Dan_Jeffries1 > Nobody seems to be able to recreate the verbatim output with the BS prompts they provided. You can trivially reproduce exact articles word-for-word from a variety of sources with the legacy completion model and GPT3.5

0

6

Dylan Freedman

@dylfreed

3 years

Thank you to @morisy and Mitch for leading such an innovative and supportive team. If you're looking to work with passionate folks, have full remote flexibility, and helm a widely used and respected product, please apply. It's an incredible opportunity!

DocumentCloud

@documentcloud

3 years

Are you a software developer wanting to help power journalism, transparency & accountability for millions of people each month? A data journalist who wants to shift to building apps & managing a platform? We're hiring!

1

16

13

1

2

6

Dylan Freedman

@dylfreed

2 years

@alpv95 @taylorhowell @simonlc_ Video frame rate perfectly synced to rotor RPM, clearly

1

0

6

Dylan Freedman

@dylfreed

7 years

Just published my personal website, which details some of my projects in code, journalism, and music. (I used the new web app framework Sapper to make the site quick and snappy @sveltejs )

0

6

Dylan Freedman

@dylfreed

28 days

@simonw @Jonathan_Adly_ Perhaps OCRBench? Not yet updated with Qwen2-VL models

Ocrbench Leaderboard - a Hugging Face Space by echo840

huggingface.co

0

6

Dylan Freedman

@dylfreed

3 years

Excited to share that our live German election results page is up and running! 🔥 It's the first election I've helped work on — and the Post's first live results page for an international election 🇩🇪

2021 German election results | The Washington Post

Live-updating vote counts, and analysis of the 2021 German parliamentary election from The Washington Post.

www.washingtonpost.com

0

1

6

Dylan Freedman

@dylfreed

6 years

Who said “Dank Learning” was just a viral research paper? Happy to say my Stanford roommate and I have turned his scholarship into an iPhone app that generates memes with AI. Original paper: (p.s. we don’t endorse offensive memes)

0

1

6

Dylan Freedman

@dylfreed

4 years

I've updated with the latest data from @nytimes . New features: 1⃣ Auto-updates with live counts for the current day 2⃣ 🇵🇷 Puerto Rico added 🇵🇷 3⃣ Type 'c' to show counties with more new cases/deaths compared to the previous day (toggleable in settings)

1

5

Dylan Freedman

@dylfreed

7 years

Read about the secret life of Bay Area mountain lions and the community capturing them on camera in my latest piece in @SFGate

Elusive: Recording the Secret Lives of Bay Area Mountain Lions

Deep in the Santa Cruz mountains, Rob Fulton and Daniel DeLong both run Facebook groups where they and others post trail camera footage of local mountain lio...

www.youtube.com

0

5

Dylan Freedman

@dylfreed

2 years

@simonw @bxroberts @WapoEngineering We had an initial version of the tool that looked similar to @simonw 's. The key innovations of the new algo: 1) breaking apart the names into alphanumeric parts, 2) identifying perfect part matches, and 3) minimum edit distance on permutations of the remaining parts

2

0

5

Dylan Freedman

@dylfreed

2 years

TIL you can drag the Zoom squares around to rearrange them

0

5

Dylan Freedman

@dylfreed

1 year

@palewire @MeghanHoyer I’d love to partner with journalists interested in extracting information from tranches of documents and put together more training materials. For myself I’ve had some fun learning from old classics and public domain books — it’s a really unique way to get to know a work!

1

0

5

Dylan Freedman

@dylfreed

2 years

Though it is unfortunate that only large, well-funded tech companies can afford to build very high-quality OCR models. And they are almost always closed source 💸

0

5

Dylan Freedman

@dylfreed

1 month

Amazing how simple this one is

Omar Khattab

@lateinteraction

1 month

Fascinatingly basic hallucination. Every time you resample you seemingly get a different random answer? (I had expected that they provide the time in the system prompt or something.)

29

7

156

1

0

5

Dylan Freedman

@dylfreed

3 months

What is "AI intelligence," @OpenAI ?

1

0

5

Dylan Freedman

@dylfreed

2 years

@simonw @bxroberts @WapoEngineering Yes, it's a single page static application. So along with open sourcing it soon, we'll have a public nice URL for it too :)

0

5

Dylan Freedman

@dylfreed

2 years

. @lennybronner and his team used Crosswalker during the 2022 Midterm Elections to match precinct names. It was helpful to quickly construct crosswalks for The Washington Post Election Model when states released new precinct names just hours beforehand.

1

0

4

Dylan Freedman

@dylfreed

2 years

@hodgesmr @simonw Yea I also read it that way. Thaler was requesting the AI be credited as author, or as a hired contractor — both of which go against the clearly established human copyright/contract holder precedent. I’d imagine most prompt-design AI art could be argued to be transformative.

1

0

4

Dylan Freedman

@dylfreed

2 years

@jeremybowers @tmcw How dare something else introduce bugs into my code. Only I do that!

1

0

4

Dylan Freedman

@dylfreed

2 years

My @figma widget was approved! Search “code editor” in widgets or check the link below to try it out. (I mainly made it because I wanted to diagram APIs in 2d space with @typescript interfaces)

Code Editor | Figma

A code editor that enables you to write syntax-highlighted source code in several languages. Features: framed/unframed styleslight and dark modefont size Language support: JavaScript (with support...

www.figma.com

Dylan Freedman

@dylfreed

2 years

#WeekendProject Experimenting with @figma 's new widget API to make a code editor. This uses @codemirror under-the-hood and outputs Figma components. Plus there's a few style options 🎨

1

0

3

0

4

Dylan Freedman

@dylfreed

3 years

✨ Work-in-progress source code here: Thanks to @sveltejs 's SvelteKit for powering the server, the Mermaid library for providing quick flowcharts, and @typescript for making it easy to model the data

GitHub - freedmand/stepfunction-visualizer: A toolkit to debug and visualize local AWS step...

A toolkit to debug and visualize local AWS step functions - freedmand/stepfunction-visualizer

github.com

0

4

Dylan Freedman

@dylfreed

1 year

If you have any questions about anything, please reach out! My DMs are open, or email dylan.freedman @washpost .com

2

1

4

Dylan Freedman

@dylfreed

2 years

@emilymbender @simonw @knowtheory @vlordier @robroc @mtdukes Just to throw more thoughts into the void: humans constantly seek "magic" to enrich their lives. Its pursuit drives innovation. But I'd liken AI more to "alchemy" than anything — conflating machine outputs with human thought/intention/art/truth is an impossibly twisted pursuit.

3

0

4