Author Archives: Edwin K

Introduction to Leo 0.5

Sometimes you want to follow high volume publications like The Verge, NY Times, or VentureBeat because you trust them but you are only interested in narrower topics, trends, or mentions.

Reducing noise and information overload is a problem we care passionately about. We have been working over the last 12 months on a new feature called Leo. You can think of Leo as your non-black-box research assistant – an easy-to-control AI tool which helps you reduce noise in your feeds and never miss important articles.

Here is a quick overview of the Leo 0.5 Beta feature set.

New Priority Tab

If you are part of the Leo 0.5 Beta Program, each of your feeds has now 2 tabs.

Introducing the new Priority Tab

The All Tab includes all the articles published by the sources you follow.

The new Priority Tab includes the subset of articles flag by Leo as important – based on the priorities you defined for your Leo.

Three Core Prioritization Skills: Mentions, Topics, and Like Board

Leo 0.5 ships with three core skills: mentions, topics, and like-board. Each of these skills allow you to prioritize articles differently.

The mentions skill allows you to prioritize articles based on mentions of people, company or keywords which are important to you.

Ask Leo to prioritize articles mentioning JP Morgan

For example, you can ask Leo to prioritize all the articles that mention “JP Morgan”

The topic skill allow you to prioritize articles which are about a specific topic you are interested.

Ask Leo to prioritize articles about quantum computing

For example, you can ask Leo to analyze your tech feed and prioritize articles which are about artificial intelligence, quantum computing, or gaming.

Leo ships with one thousand pre-trained topics. If the topic you are interested in is part of that list, the topic skill is a powerful tool to let you focus your feed on what really matters to you.

Sometimes, the topic you are interested in a very niche. This is where the Like Board skill is very useful and powerful.

Prioritize articles similar to the ones saved in your Smart Venue board

For example, if you are in the Sports industry, you might be interested in the emerging Smart Venue trend. Leo does not know out of the box about Smart Venue but if you can create a board and save 30-50 articles about Smart Venue, you can use the Like Board skill to teach your Leo a new personalized topic and ask Leo to prioritize future articles which are similar to the ones you save in that board.

Once you have defined the priorities of your Leo, he will continuously read your feed and flag articles which are aligned with those priorities.

The Like Board is particularly powerful because the more articles you save to that board, the more accurate Leo’s recommendation will become.

Finally, you can easily define more sophisticated priorities by combining multiple skills/layers.

Combine multiple layers

Feedback Loop Via Less Like This

When Leo makes a back prioritization, you have the control to provide him feedback via the Less Like This button.

Provide Leo feedback via Less Like This

There are 5 different classes of feedback you can offer to your Leo:

  1. The “Not About” feedback allows you to teach Leo that it matched the wrong keyword or topic. For example, you were interested in ICO (Initial Coin Offering) and Leo detected ICO (Internet Commissioner Office).
  2. The “duplicated article” feedback allow you to flag articles which are on topic but you have already read about via a different source
  3. The “I’m not interested in” feedback allow you to flag class of articles you are not interested about. For example, you might not be interested in market research type articles. If you can flag 10-20 articles as I am not interested in market research, Leo is going to learn and start prioritizing fewer market research articles.
  4. Sometimes (specially for keyword alerts), you might get articles from sources you do not care about. The ‘mute domain’ feedback allows you to train your Leo to mute articles from those domains.
  5. Finally, sometimes, the reason is more complex. The ‘Something else’ feedback offers you an easy way out.

Deduplication

We also heard from a lot of users that duplicate articles are a big source of noise and echo in their feeds. If you are tired of seeing the same article or press release being pushed across multiple sources, Leo 0.5 near exact deduplication is here to help.

A sign at the bottom right shows the count of duplicates which are automatically removed

Leo continuously monitors your feeds and when he detects duplicates, it automatically clean up your feeds so that you only get one copy of the article or press release.

This is particularly useful if you follow a lot of Google Keyword Alerts or if you follow source that cross post content.

Control and Transparency

A very important aspect of the Leo promise is that it is a fun, non-black-box AI you fully control and can easily collaborate with.

Transparency via clear explanations

Transparent because each time Leo makes a prioritization, he will explain why the article was prioritized and give you the opportunity to refine that prioritization.

Full control

Control because you explicitly define all the priorities of your Leo and you can at anytime go in the Train Leo section and remove or refine a priority. No black box. No lag.

Goodbye Information Overload

Leo 0.1 Alpha customers saw 40-70% noise reduction on their feeds. More targeted feeds mean that you can save time while reducing the risk of missing important articles, or being the last to know about an important risk or market opportunity.

We look forward to seeing how your will be training your Leo!

-Edwin, Remi, and Victoria

Introduction to Leo 0.5

Sometimes you want to follow high volume publications like The Verge, NY Times, or VentureBeat because you trust them but you are only interested in narrower topics, trends, or mentions.

Reducing noise and information overload is a problem we care passionately about. We have been working over the last 12 months on a new feature called Leo. You can think of Leo as your non-black-box research assistant – an easy-to-control AI tool which helps you reduce noise in your feeds and never miss important articles.

Here is a quick overview of the Leo 0.5 Beta feature set.

New Priority Tab

If you are part of the Leo 0.5 Beta Program, each of your feeds has now 2 tabs.

Introducing the new Priority Tab

The All Tab includes all the articles published by the sources you follow.

The new Priority Tab includes the subset of articles flag by Leo as important – based on the priorities you defined for your Leo.

Three Core Prioritization Skills: Mentions, Topics, and Like Board

Leo 0.5 ships with three core skills: mentions, topics, and like-board. Each of these skills allow you to prioritize articles differently.

The mentions skill allows you to prioritize articles based on mentions of people, company or keywords which are important to you.

Ask Leo to prioritize articles mentioning JP Morgan

For example, you can ask Leo to prioritize all the articles that mention “JP Morgan”

The topic skill allow you to prioritize articles which are about a specific topic you are interested.

Ask Leo to prioritize articles about quantum computing

For example, you can ask Leo to analyze your tech feed and prioritize articles which are about artificial intelligence, quantum computing, or gaming.

Leo ships with one thousand pre-trained topics. If the topic you are interested in is part of that list, the topic skill is a powerful tool to let you focus your feed on what really matters to you.

Sometimes, the topic you are interested in a very niche. This is where the Like Board skill is very useful and powerful.

Prioritize articles similar to the ones saved in your Smart Venue board

For example, if you are in the Sports industry, you might be interested in the emerging Smart Venue trend. Leo does not know out of the box about Smart Venue but if you can create a board and save 30-50 articles about Smart Venue, you can use the Like Board skill to teach your Leo a new personalized topic and ask Leo to prioritize future articles which are similar to the ones you save in that board.

Once you have defined the priorities of your Leo, he will continuously read your feed and flag articles which are aligned with those priorities.

The Like Board is particularly powerful because the more articles you save to that board, the more accurate Leo’s recommendation will become.

Finally, you can easily define more sophisticated priorities by combining multiple skills/layers.

Combine multiple layers

Feedback Loop Via Less Like This

When Leo makes a back prioritization, you have the control to provide him feedback via the Less Like This button.

Provide Leo feedback via Less Like This

There are 5 different classes of feedback you can offer to your Leo:

  1. The “Not About” feedback allows you to teach Leo that it matched the wrong keyword or topic. For example, you were interested in ICO (Initial Coin Offering) and Leo detected ICO (Internet Commissioner Office).
  2. The “duplicated article” feedback allow you to flag articles which are on topic but you have already read about via a different source
  3. The “I’m not interested in” feedback allow you to flag class of articles you are not interested about. For example, you might not be interested in market research type articles. If you can flag 10-20 articles as I am not interested in market research, Leo is going to learn and start prioritizing fewer market research articles.
  4. Sometimes (specially for keyword alerts), you might get articles from sources you do not care about. The ‘mute domain’ feedback allows you to train your Leo to mute articles from those domains.
  5. Finally, sometimes, the reason is more complex. The ‘Something else’ feedback offers you an easy way out.

Deduplication

We also heard from a lot of users that duplicate articles are a big source of noise and echo in their feeds. If you are tired of seeing the same article or press release being pushed across multiple sources, Leo 0.5 near exact deduplication is here to help.

A sign at the bottom right shows the count of duplicates which are automatically removed

Leo continuously monitors your feeds and when he detects duplicates, it automatically clean up your feeds so that you only get one copy of the article or press release.

This is particularly useful if you follow a lot of Google Keyword Alerts or if you follow source that cross post content.

Control and Transparency

A very important aspect of the Leo promise is that it is a fun, non-black-box AI you fully control and can easily collaborate with.

Transparency via clear explanations

Transparent because each time Leo makes a prioritization, he will explain why the article was prioritized and give you the opportunity to refine that prioritization.

Full control

Control because you explicitly define all the priorities of your Leo and you can at anytime go in the Train Leo section and remove or refine a priority. No black box. No lag.

Goodbye Information Overload

Leo 0.1 Alpha customers saw 40-70% noise reduction on their feeds. More targeted feeds mean that you can save time while reducing the risk of missing important articles, or being the last to know about an important risk or market opportunity.

We look forward to seeing how your will be training your Leo!

-Edwin, Remi, and Victoria

Premium Fonts

Feedly Labs has been a really interesting experience for us because it has helped us get a deeper understanding of who the Feedly community is and how we can better serve you going forward.

One of the insights we learned last fall is that the community seems to care deeply about typography.

Conversation on Feedly Lab

Based on that insight, we funded a project focused on giving you more control over fonts and font size through a close partnership with Monotype (one of the best foundries in the world).

Today, we are excited to announce the fruits of that project – which will be available on the Web today and on Mobile, next week.

ITC Charter
Mundo Sans and larger font size
DinNext

Open Dyslexic Experiment

Dyslexia is also very close to our heart. People with dyslexia have normal intelligence and vision but might have difficulty reading due to problems identifying speech sounds and learning how they relate to letters and words (decoding).

Open Dyslexic

Some fonts have been emerging which are designed around the common symptoms of dyslexia. We decided as part of the premium fonts project to add support for Open Dyslexic and see if switching to that font can help with the decoding or not. If you are suffering from Dyslexia and want to provide us feedback on how we could help make Feedly better, please join the Feedly Lab.

Google Noto and support for more languages

Last but not least, we are have added support for the Google Noto, which is a beautiful font which works well across lots of languages.

Google Noto

If you are consuming lots of international content and need a font preference that works across lots of languages, it might be a very good choice.

Getting started with Fonts

On mobile, you can use the Aa menu which is available in the article viewer to change your font settings (and theme). On the web, you can go to your account settings > appearance.

Some fonts are free and they are available in the free Feedly Basic Plan. Some fonts are premium and they are part of the Feedly Pro and Feedly Team plans.

We love that the idea for this feature emerged from the Feedly Lab. If you love the Web and love reading and what to provide feedback and share ideas with the team, please join the Feedly Lab.

Happy reading!

-The Feedly Team

Premium Fonts

Feedly Labs has been a really interesting experience for us because it has helped us get a deeper understanding of who the Feedly community is and how we can better serve you going forward.

One of the insights we learned last fall is that the community seems to care deeply about typography.

Conversation on Feedly Lab

Based on that insight, we funded a project focused on giving you more control over fonts and font size through a close partnership with Monotype (one of the best foundries in the world).

Today, we are excited to announce the fruits of that project – which will be available on the Web today and on Mobile, next week.

ITC Charter
Mundo Sans and larger font size
DinNext

Open Dyslexic Experiment

Dyslexia is also very close to our heart. People with dyslexia have normal intelligence and vision but might have difficulty reading due to problems identifying speech sounds and learning how they relate to letters and words (decoding).

Open Dyslexic

Some fonts have been emerging which are designed around the common symptoms of dyslexia. We decided as part of the premium fonts project to add support for Open Dyslexic and see if switching to that font can help with the decoding or not. If you are suffering from Dyslexia and want to provide us feedback on how we could help make Feedly better, please join the Feedly Lab.

Google Noto and support for more languages

Last but not least, we are have added support for the Google Noto, which is a beautiful font which works well across lots of languages.

Google Noto

If you are consuming lots of international content and need a font preference that works across lots of languages, it might be a very good choice.

Getting started with Fonts

On mobile, you can use the Aa menu which is available in the article viewer to change your font settings (and theme). On the web, you can go to your account settings > appearance.

Some fonts are free and they are available in the free Feedly Basic Plan. Some fonts are premium and they are part of the Feedly Pro and Feedly Team plans.

We love that the idea for this feature emerged from the Feedly Lab. If you love the Web and love reading and what to provide feedback and share ideas with the team, please join the Feedly Lab.

Happy reading!

-The Feedly Team

Deduplication Skill – Leo

It is frustrating to be skimming through your feeds and run into duplicate articles.

This happens for example when you have overlapping keyword alerts where two different keywords exist in the same article. It also happens when some sources publish the same articles into different RSS feeds. Finally, it happens a lot when a company issues a press release and other sources publish that press release with some minor changes.

Giving you the tools and control to tune your feeds is something we care passionately about. Today, we are excited to announce the beta release of a new Leo skill called Deduplication.

What is Deduplication?

This skill helps Leo detect that multiple articles are near exact duplicates of each other and cut that noise from your feeds. On the Web version of Feedly, you will see a small notification at the bottom right of your screen each time Leo removes duplicate from your feeds.

Which language does Deduplication work on?

The Leo deduplication skill works across all languages?

Which Feedly Plan does this skill require?

Because processing duplicates at scale is expensive, this skill will be initially rolled out as part of the Feedly Teams plan.

If you are part of Feedly Teams, there is a preference knob in the Leo settings page to disable this skill.

Beyond near exact duplicates

The deduplication skill is focusing on near exact duplicates. These are articles which have 85% or more overlap. We are working on a different skill called Business Events for articles which are reporting on the same event but with different content. In the case of business events, the content will be grouped instead of being removed.

Thank you!

We want to thank you Aymeric Bernard and Iheb Benabdallah for doing the preliminary ML research behind this Leo skill!

Deduplication Skill – Leo

It is frustrating to be skimming through your feeds and run into duplicate articles.

This happens for example when you have overlapping keyword alerts where two different keywords exist in the same article. It also happens when some sources publish the same articles into different RSS feeds. Finally, it happens a lot when a company issues a press release and other sources publish that press release with some minor changes.

Giving you the tools and control to tune your feeds is something we care passionately about. Today, we are excited to announce the beta release of a new Leo skill called Deduplication.

What is Deduplication?

This skill helps Leo detect that multiple articles are near exact duplicates of each other and cut that noise from your feeds. On the Web version of Feedly, you will see a small notification at the bottom right of your screen each time Leo removes duplicate from your feeds.

Which language does Deduplication work on?

The Leo deduplication skill works across all languages?

Which Feedly Plan does this skill require?

Because processing duplicates at scale is expensive, this skill will be initially rolled out as part of the Feedly Teams plan.

If you are part of Feedly Teams, there is a preference knob in the Leo settings page to disable this skill.

Beyond near exact duplicates

The deduplication skill is focusing on near exact duplicates. These are articles which have 85% or more overlap. We are working on a different skill called Business Events for articles which are reporting on the same event but with different content. In the case of business events, the content will be grouped instead of being removed.

Thank you!

We want to thank you Aymeric Bernard and Iheb Benabdallah for doing the preliminary ML research behind this Leo skill!

Experiment 08 – New Compact Magazine View Option

Listening to the murmurs in the Lab Slack channel, it seems that controlling the density of the articles is important to the community. Some users like to see a mix of images with the article summary, some people prefer to see only text, some people want more density, some less. In Experiment 08, we took that feedback into account and added a new density preference which can be applied to text only, magazine, and card views. The result is more control over how you want to consume your feeds.

Note: The view and density settings can be configured for each source, feed, or board. There is also a global option in the app settings.

New icons

As part of Experiment 08, we are pushing out the new set of icons (designed by the talented Daniel Klopper)

Polish and bug fixes

The team also took advantage of the Experiment 08 build to fix the following bugs and rough edges:

  • Added button to go from no unread to all articles (Thank you Daron, John, Rogerio)
  • Return to feed list after swiping the last/first article (Thank you Peter & Scott)
  • We added support for Firefox and Chrome as favorite browsers on iOS (Thank you Donhack, Peter, Jon)
  • We fixed an authentication error related to trying to login to Google in a webview (Thank you P and Anks)
  • We fixed the iPad framing bug at first launch (Thank you Michal)
  • We fixed the image loading issue where sometimes the preview would show an image but not the opened article (Thank you Mark)
  • We fixed the long titles in header bug (Thank you Chip)
  • We improved the Youtube integration (Thank you Seb)
  • After refresh at the end of the Today page, we are not staying on the Today page (Thank you Paavo)
  • We added an option to open a source from an inlined article by tapping on the source name (Thank you Xeor)
  • Separated auto-mark as read between mobile and Web. You will have to re-select auto-mark as read on scroll in the mobile settings if you want to activate it.
  • Improved discover search auto-completion history experience (Thank you Jesse)
  • We polished the back mode of the paged scrolling option (Thank you #paged-scrolling)
  • We fixed the conflict between the text selection and the close gestures
  • Refreshing the All page after mark as read in the All page footer (Thank you Dallas)
  • Fixed rename source bug (Thank you Dallas)
  • Make discover language sticky (Thank you Eduardo)

Next: Switching the Classic App and the Lab App

The next two weeks are about fixing bugs and rough edges and getting to the point where we can replace the classic app with the new lab app. Your feedback is going to be extremely useful during that time. Once you have 48.0.2 installed, if you experience any bug or run into a part of the experience which does not feel polished, please add a message to the #bugs Slack channel. The dev team will be actively monitoring that channel and try to fix as many bugs and rough edges as possible.

Experiment 08 – New Compact Magazine View Option

Listening to the murmurs in the Lab Slack channel, it seems that controlling the density of the articles is important to the community. Some users like to see a mix of images with the article summary, some people prefer to see only text, some people want more density, some less. In Experiment 08, we took that feedback into account and added a new density preference which can be applied to text only, magazine, and card views. The result is more control over how you want to consume your feeds.

Note: The view and density settings can be configured for each source, feed, or board. There is also a global option in the app settings.

New icons

As part of Experiment 08, we are pushing out the new set of icons (designed by the talented Daniel Klopper)

Polish and bug fixes

The team also took advantage of the Experiment 08 build to fix the following bugs and rough edges:

  • Added button to go from no unread to all articles (Thank you Daron, John, Rogerio)
  • Return to feed list after swiping the last/first article (Thank you Peter & Scott)
  • We added support for Firefox and Chrome as favorite browsers on iOS (Thank you Donhack, Peter, Jon)
  • We fixed an authentication error related to trying to login to Google in a webview (Thank you P and Anks)
  • We fixed the iPad framing bug at first launch (Thank you Michal)
  • We fixed the image loading issue where sometimes the preview would show an image but not the opened article (Thank you Mark)
  • We fixed the long titles in header bug (Thank you Chip)
  • We improved the Youtube integration (Thank you Seb)
  • After refresh at the end of the Today page, we are not staying on the Today page (Thank you Paavo)
  • We added an option to open a source from an inlined article by tapping on the source name (Thank you Xeor)
  • Separated auto-mark as read between mobile and Web. You will have to re-select auto-mark as read on scroll in the mobile settings if you want to activate it.
  • Improved discover search auto-completion history experience (Thank you Jesse)
  • We polished the back mode of the paged scrolling option (Thank you #paged-scrolling)
  • We fixed the conflict between the text selection and the close gestures
  • Refreshing the All page after mark as read in the All page footer (Thank you Dallas)
  • Fixed rename source bug (Thank you Dallas)
  • Make discover language sticky (Thank you Eduardo)

Next: Switching the Classic App and the Lab App

The next two weeks are about fixing bugs and rough edges and getting to the point where we can replace the classic app with the new lab app. Your feedback is going to be extremely useful during that time. Once you have 48.0.2 installed, if you experience any bug or run into a part of the experience which does not feel polished, please add a message to the #bugs Slack channel. The dev team will be actively monitoring that channel and try to fix as many bugs and rough edges as possible.