Matthew Honnibal
@honnibal.bsky.social
Computational linguist from Sydney and Berlin.
Author of the spacy.io NLP tools
Founder and CTO @explosion.ai
LinkedIn: linkedin.com/in/honnibal
Blog: honnibal.dev
Author of the spacy.io NLP tools
Founder and CTO @explosion.ai
LinkedIn: linkedin.com/in/honnibal
Blog: honnibal.dev
I feel like my Claude Code got a lot worse after I made some grumpy changes to my system prompt. I was annoyed that it kept trying to condition around invalid data instead of failing and fixing the data at the source, so I added some instructions to the prompt that were maybe too blunt. However...
June 10, 2025 at 10:38 AM
I feel like my Claude Code got a lot worse after I made some grumpy changes to my system prompt. I was annoyed that it kept trying to condition around invalid data instead of failing and fixing the data at the source, so I added some instructions to the prompt that were maybe too blunt. However...
Reposted by Matthew Honnibal
I'm back from a busy four days in London! 💜 I had a great time at @pydatalondon.bsky.social and you can read my recap and highlights here: www.linkedin.com/feed/update/...
June 9, 2025 at 7:13 AM
I'm back from a busy four days in London! 💜 I had a great time at @pydatalondon.bsky.social and you can read my recap and highlights here: www.linkedin.com/feed/update/...
Reposted by Matthew Honnibal
Hi Berlin people! @hugobowne.bsky.social is in town & we're celebrating by hosting a meetup together 🎉 This one is all about building with AI & we'll also open the floor for lightning talks. If you're around, come hang out with us!
📆 June 16, 18:00
📍 Native Instruments (Kreuzberg)
🎟️ lu.ma/d53y9p2u
📆 June 16, 18:00
📍 Native Instruments (Kreuzberg)
🎟️ lu.ma/d53y9p2u
June 2, 2025 at 7:48 AM
Hi Berlin people! @hugobowne.bsky.social is in town & we're celebrating by hosting a meetup together 🎉 This one is all about building with AI & we'll also open the floor for lightning talks. If you're around, come hang out with us!
📆 June 16, 18:00
📍 Native Instruments (Kreuzberg)
🎟️ lu.ma/d53y9p2u
📆 June 16, 18:00
📍 Native Instruments (Kreuzberg)
🎟️ lu.ma/d53y9p2u
Back to streaming spaCy! Working on Python 3.13 compatibility today: www.youtube.com/watch?v=wgjQ...
Streaming spaCy (May 19, 2025): Working on Python 3.13 compatibility
YouTube video by Explosion
www.youtube.com
May 19, 2025 at 10:07 AM
Back to streaming spaCy! Working on Python 3.13 compatibility today: www.youtube.com/watch?v=wgjQ...
Reposted by Matthew Honnibal
Another great @pyconde.bsky.social is over and I'm exhausted but happy, and feel very inspired! ⚡
Here are my personal highlights: www.linkedin.com/feed/update/...
Here are my personal highlights: www.linkedin.com/feed/update/...
April 26, 2025 at 9:11 AM
Another great @pyconde.bsky.social is over and I'm exhausted but happy, and feel very inspired! ⚡
Here are my personal highlights: www.linkedin.com/feed/update/...
Here are my personal highlights: www.linkedin.com/feed/update/...
Reposted by Matthew Honnibal
My friend @hugobowne.bsky.social launched new course on Building LLM Applications for Data Scientists and Software Engineers! I'll be joining for a guest lecture on human-in-the-loop development and distillation workflows.
You can get 10% off with my code + lots of perks: maven.com/hugo-stefan/...
You can get 10% off with my code + lots of perks: maven.com/hugo-stefan/...
April 5, 2025 at 6:14 AM
My friend @hugobowne.bsky.social launched new course on Building LLM Applications for Data Scientists and Software Engineers! I'll be joining for a guest lecture on human-in-the-loop development and distillation workflows.
You can get 10% off with my code + lots of perks: maven.com/hugo-stefan/...
You can get 10% off with my code + lots of perks: maven.com/hugo-stefan/...
Reposted by Matthew Honnibal
I don't normally write advice columns but this question I got deserved its own post: With all the hype around Generative AI, how can you, as a developer, communicate the nuances and advocate for new and modular solutions that are better, easier and cheaper?
explosion.ai/blog/modular...
explosion.ai/blog/modular...
March 31, 2025 at 11:48 AM
I don't normally write advice columns but this question I got deserved its own post: With all the hype around Generative AI, how can you, as a developer, communicate the nuances and advocate for new and modular solutions that are better, easier and cheaper?
explosion.ai/blog/modular...
explosion.ai/blog/modular...
Reposted by Matthew Honnibal
So many good events coming up this season. Here's my schedule – hope to see you there!
Apr 10: data:unplugged (Münster)
Apr 23: @pyconde.bsky.social (Darmstadt)
May 31: @pyconit.bsky.social (Bologna)
Jun 5: ECONDAT (London)
Jun 7-8: @pydatalondon.bsky.social (London)
📆 Details: explosion.ai/events
Apr 10: data:unplugged (Münster)
Apr 23: @pyconde.bsky.social (Darmstadt)
May 31: @pyconit.bsky.social (Bologna)
Jun 5: ECONDAT (London)
Jun 7-8: @pydatalondon.bsky.social (London)
📆 Details: explosion.ai/events
March 29, 2025 at 11:06 AM
So many good events coming up this season. Here's my schedule – hope to see you there!
Apr 10: data:unplugged (Münster)
Apr 23: @pyconde.bsky.social (Darmstadt)
May 31: @pyconit.bsky.social (Bologna)
Jun 5: ECONDAT (London)
Jun 7-8: @pydatalondon.bsky.social (London)
📆 Details: explosion.ai/events
Apr 10: data:unplugged (Münster)
Apr 23: @pyconde.bsky.social (Darmstadt)
May 31: @pyconit.bsky.social (Bologna)
Jun 5: ECONDAT (London)
Jun 7-8: @pydatalondon.bsky.social (London)
📆 Details: explosion.ai/events
Reposted by Matthew Honnibal
@explosion-ai.bsky.social
Only the best companies will send you stickers if you are a fan and beg for them!
Thank you so much, Ines and Matt!!!!
Only the best companies will send you stickers if you are a fan and beg for them!
Thank you so much, Ines and Matt!!!!
March 13, 2025 at 2:22 PM
@explosion-ai.bsky.social
Only the best companies will send you stickers if you are a fan and beg for them!
Thank you so much, Ines and Matt!!!!
Only the best companies will send you stickers if you are a fan and beg for them!
Thank you so much, Ines and Matt!!!!
Reposted by Matthew Honnibal
New case study: How Love Without Sound built innovative AI-powered tools for the music industry and law firms, and helped publishers recover hundreds of millions of dollars in lost revenue for artists.
explosion.ai/blog/love-wi...
explosion.ai/blog/love-wi...
March 24, 2025 at 11:10 AM
New case study: How Love Without Sound built innovative AI-powered tools for the music industry and law firms, and helped publishers recover hundreds of millions of dollars in lost revenue for artists.
explosion.ai/blog/love-wi...
explosion.ai/blog/love-wi...
Reposted by Matthew Honnibal
Out now: Prodigy v1.18! New features include:
✍️ edit text during span annotation
💬 fully custom UI translations
🎛️ new JavaScript events and functions
✅ various small fixes and docs
More details: prodi.gy/docs/changelog
✍️ edit text during span annotation
💬 fully custom UI translations
🎛️ new JavaScript events and functions
✅ various small fixes and docs
More details: prodi.gy/docs/changelog
February 25, 2025 at 11:38 AM
Out now: Prodigy v1.18! New features include:
✍️ edit text during span annotation
💬 fully custom UI translations
🎛️ new JavaScript events and functions
✅ various small fixes and docs
More details: prodi.gy/docs/changelog
✍️ edit text during span annotation
💬 fully custom UI translations
🎛️ new JavaScript events and functions
✅ various small fixes and docs
More details: prodi.gy/docs/changelog
Reposted by Matthew Honnibal
These are the kinds of NLP stories I love! TFW you "accidentally" train a great 2 MB (!) task-specific model 🤯 @strickvl.bsky.social
February 14, 2025 at 9:43 AM
These are the kinds of NLP stories I love! TFW you "accidentally" train a great 2 MB (!) task-specific model 🤯 @strickvl.bsky.social
Reposted by Matthew Honnibal
Look what arrived in the mail today! 🎉
This is the 2nd edition of "Mastering spaCy" by Duygu Altinok and Déborah Mesquita, featuring how to build structured NLP solutions with custom components, and updated content on using models powered by LLMs.
You can get it here: www.amazon.com/dp/B0DVBTX2BL
This is the 2nd edition of "Mastering spaCy" by Duygu Altinok and Déborah Mesquita, featuring how to build structured NLP solutions with custom components, and updated content on using models powered by LLMs.
You can get it here: www.amazon.com/dp/B0DVBTX2BL
February 13, 2025 at 4:52 PM
Look what arrived in the mail today! 🎉
This is the 2nd edition of "Mastering spaCy" by Duygu Altinok and Déborah Mesquita, featuring how to build structured NLP solutions with custom components, and updated content on using models powered by LLMs.
You can get it here: www.amazon.com/dp/B0DVBTX2BL
This is the 2nd edition of "Mastering spaCy" by Duygu Altinok and Déborah Mesquita, featuring how to build structured NLP solutions with custom components, and updated content on using models powered by LLMs.
You can get it here: www.amazon.com/dp/B0DVBTX2BL
spaCy development live stream continues today! Today I'll be looking at getting Confection updated, to allow Python 3.13 support and add a file-management feature. Playlist: www.youtube.com/watch?v=TTEW...
The spaCy+PyTorch design has been going well, but we need that file management feature now.
The spaCy+PyTorch design has been going well, but we need that file management feature now.
Streaming spaCy (Feb 6, 2025): Updating Confection for Python 3.13 and more
YouTube video by Explosion
www.youtube.com
February 6, 2025 at 1:08 PM
spaCy development live stream continues today! Today I'll be looking at getting Confection updated, to allow Python 3.13 support and add a file-management feature. Playlist: www.youtube.com/watch?v=TTEW...
The spaCy+PyTorch design has been going well, but we need that file management feature now.
The spaCy+PyTorch design has been going well, but we need that file management feature now.
Pretty happy with how the spaCy+PyTorch design is coming together. And hopefully I'll continue to get smoother at streaming :)
www.youtube.com/watch?v=YeKi...
www.youtube.com/watch?v=YeKi...
January 31, 2025 at 12:27 PM
Pretty happy with how the spaCy+PyTorch design is coming together. And hopefully I'll continue to get smoother at streaming :)
www.youtube.com/watch?v=YeKi...
www.youtube.com/watch?v=YeKi...
Live again now, doing more design work on what it would look like if we rebuilt spaCy on PyTorch: www.youtube.com/watch?v=fzFH...
January 30, 2025 at 1:36 PM
Live again now, doing more design work on what it would look like if we rebuilt spaCy on PyTorch: www.youtube.com/watch?v=fzFH...
Reposted by Matthew Honnibal
Enjoyed giving my keynote on "What the history of the web can teach us about the future of AI" at PyCon+Web. I wrote it up as a blog post because I think there are many interesting parallels and lessons we can learn:
explosion.ai/blog/history...
Here are the most important points 🧵
explosion.ai/blog/history...
Here are the most important points 🧵
What the history of the web can teach us about the future of AI · Explosion
How will AI development look in the future? There is a lot we can learn from another groundbreaking technology: the web. This blog post takes a look at what the history of the web can teach us, and wh...
explosion.ai
January 27, 2025 at 12:01 PM
Enjoyed giving my keynote on "What the history of the web can teach us about the future of AI" at PyCon+Web. I wrote it up as a blog post because I think there are many interesting parallels and lessons we can learn:
explosion.ai/blog/history...
Here are the most important points 🧵
explosion.ai/blog/history...
Here are the most important points 🧵
Okay let's try this again -- Live now!
Streaming software issues hopefully sorted 🤞
Streaming software issues hopefully sorted 🤞
Will do another short (~2h or so) stream this afternoon, at 13:00 CET.
Last week I was limited in what I could do because the main thing I was working on was build system stuff, and OBS was crashing when I tried to create a desktop view. This week we can look at a more interesting topic.
Last week I was limited in what I could do because the main thing I was working on was build system stuff, and OBS was crashing when I tried to create a desktop view. This week we can look at a more interesting topic.
Trying something new this year: I'm going to stream spaCy and other open-source development and maintenance twice a week!
I hope this will give the community a better inside look while things are in progress. I'll also answer your questions and chat about NLP, OSS and more.
I hope this will give the community a better inside look while things are in progress. I'll also answer your questions and chat about NLP, OSS and more.
January 17, 2025 at 12:52 PM
Okay let's try this again -- Live now!
Streaming software issues hopefully sorted 🤞
Streaming software issues hopefully sorted 🤞
Will do another short (~2h or so) stream this afternoon, at 13:00 CET.
Last week I was limited in what I could do because the main thing I was working on was build system stuff, and OBS was crashing when I tried to create a desktop view. This week we can look at a more interesting topic.
Last week I was limited in what I could do because the main thing I was working on was build system stuff, and OBS was crashing when I tried to create a desktop view. This week we can look at a more interesting topic.
Trying something new this year: I'm going to stream spaCy and other open-source development and maintenance twice a week!
I hope this will give the community a better inside look while things are in progress. I'll also answer your questions and chat about NLP, OSS and more.
I hope this will give the community a better inside look while things are in progress. I'll also answer your questions and chat about NLP, OSS and more.
January 16, 2025 at 9:44 AM
Will do another short (~2h or so) stream this afternoon, at 13:00 CET.
Last week I was limited in what I could do because the main thing I was working on was build system stuff, and OBS was crashing when I tried to create a desktop view. This week we can look at a more interesting topic.
Last week I was limited in what I could do because the main thing I was working on was build system stuff, and OBS was crashing when I tried to create a desktop view. This week we can look at a more interesting topic.
Going live now! Join me for the first pilot stream on YouTube: www.youtube.com/live/kViiI5B...
January 9, 2025 at 1:21 PM
Going live now! Join me for the first pilot stream on YouTube: www.youtube.com/live/kViiI5B...
Trying something new this year: I'm going to stream spaCy and other open-source development and maintenance twice a week!
I hope this will give the community a better inside look while things are in progress. I'll also answer your questions and chat about NLP, OSS and more.
I hope this will give the community a better inside look while things are in progress. I'll also answer your questions and chat about NLP, OSS and more.
January 6, 2025 at 11:17 AM
Trying something new this year: I'm going to stream spaCy and other open-source development and maintenance twice a week!
I hope this will give the community a better inside look while things are in progress. I'll also answer your questions and chat about NLP, OSS and more.
I hope this will give the community a better inside look while things are in progress. I'll also answer your questions and chat about NLP, OSS and more.
Reposted by Matthew Honnibal
Writing a new talk on "What the history of the web can teach us about the future of AI" 🔮 I've wanted to do this for so long because I think there are some great lessons and analogies here.
I'll be presenting it for my keynote at PyCon+Web in Berlin on Jan 25 – hope to see you there!
I'll be presenting it for my keynote at PyCon+Web in Berlin on Jan 25 – hope to see you there!
December 30, 2024 at 11:08 AM
Writing a new talk on "What the history of the web can teach us about the future of AI" 🔮 I've wanted to do this for so long because I think there are some great lessons and analogies here.
I'll be presenting it for my keynote at PyCon+Web in Berlin on Jan 25 – hope to see you there!
I'll be presenting it for my keynote at PyCon+Web in Berlin on Jan 25 – hope to see you there!
Reposted by Matthew Honnibal
Happy Birthday to me! 🥳 It feels like a good opportunity to look back at 2024, an eventful but also difficult year for me. So here's my personal review, including travel, talks, writing and various things I did and enjoyed.
ines.io/blog/year-in...
ines.io/blog/year-in...
My Year in Review 2024 · ines.io
2024 was an eventful but also difficult year for me. This is my personal summary, including travel, talks, writing and various things I did and enjoyed.
ines.io
December 14, 2024 at 11:33 AM
Happy Birthday to me! 🥳 It feels like a good opportunity to look back at 2024, an eventful but also difficult year for me. So here's my personal review, including travel, talks, writing and various things I did and enjoyed.
ines.io/blog/year-in...
ines.io/blog/year-in...
Reposted by Matthew Honnibal
New post: From PDFs to AI-ready structured data 📃✨
A deep dive into document processing, layout analysis and a modular workflow for building end-to-end document understanding and information extraction pipelines using PDFs, Word documents, scans and more.
explosion.ai/blog/pdfs-nl...
A deep dive into document processing, layout analysis and a modular workflow for building end-to-end document understanding and information extraction pipelines using PDFs, Word documents, scans and more.
explosion.ai/blog/pdfs-nl...
December 2, 2024 at 11:05 AM
New post: From PDFs to AI-ready structured data 📃✨
A deep dive into document processing, layout analysis and a modular workflow for building end-to-end document understanding and information extraction pipelines using PDFs, Word documents, scans and more.
explosion.ai/blog/pdfs-nl...
A deep dive into document processing, layout analysis and a modular workflow for building end-to-end document understanding and information extraction pipelines using PDFs, Word documents, scans and more.
explosion.ai/blog/pdfs-nl...
Reposted by Matthew Honnibal
Many of you have been asking about PDF table extraction and I finally got around to experimenting with it 👀
Here's tabular data converted with Docling + TableFormer, anchored within the document text and accessible as a pandas.DataFrame:
Here's tabular data converted with Docling + TableFormer, anchored within the document text and accessible as a pandas.DataFrame:
November 24, 2024 at 11:28 AM
Many of you have been asking about PDF table extraction and I finally got around to experimenting with it 👀
Here's tabular data converted with Docling + TableFormer, anchored within the document text and accessible as a pandas.DataFrame:
Here's tabular data converted with Docling + TableFormer, anchored within the document text and accessible as a pandas.DataFrame: