Brandon
@brandonwillard.bsky.social
I do things with ML, Bayesian statistics, and symbolic computation/compiler-related things.
https://github.com/brandonwillard
https://github.com/brandonwillard
Reposted by Brandon
Couldn't agree with this more!
The easy part is that it's clearly a very nice way to start a conversation with someone.
A secondary effect (which is a bit hard to quantify) is that doing things like this helps other people to know what things interest you, which can be a source of opportunities.
The easy part is that it's clearly a very nice way to start a conversation with someone.
A secondary effect (which is a bit hard to quantify) is that doing things like this helps other people to know what things interest you, which can be a source of opportunities.
There's a meme online, that men never forget a compliment, because they receive so few.
Researchers never forget a compliment either, particularly from someone they respect.
If you read a paper you like, let the authors know.
Researchers never forget a compliment either, particularly from someone they respect.
If you read a paper you like, let the authors know.
February 21, 2025 at 3:15 PM
Couldn't agree with this more!
The easy part is that it's clearly a very nice way to start a conversation with someone.
A secondary effect (which is a bit hard to quantify) is that doing things like this helps other people to know what things interest you, which can be a source of opportunities.
The easy part is that it's clearly a very nice way to start a conversation with someone.
A secondary effect (which is a bit hard to quantify) is that doing things like this helps other people to know what things interest you, which can be a source of opportunities.
Reposted by Brandon
Need to extract a few highlights from a news article?
Try this out. We used the article about Neural Magic's recent acquisition by Red Hat.
You can even change your structure to easily add reasoning and observations for better output quality.
Check the gist out: https://buff.ly/4hhCFVz
Try this out. We used the article about Neural Magic's recent acquisition by Red Hat.
You can even change your structure to easily add reasoning and observations for better output quality.
Check the gist out: https://buff.ly/4hhCFVz
January 15, 2025 at 10:19 PM
Need to extract a few highlights from a news article?
Try this out. We used the article about Neural Magic's recent acquisition by Red Hat.
You can even change your structure to easily add reasoning and observations for better output quality.
Check the gist out: https://buff.ly/4hhCFVz
Try this out. We used the article about Neural Magic's recent acquisition by Red Hat.
You can even change your structure to easily add reasoning and observations for better output quality.
Check the gist out: https://buff.ly/4hhCFVz
Reposted by Brandon
Happy building this week, everyone! Let us know what you're excited about working on.
January 13, 2025 at 6:25 PM
Happy building this week, everyone! Let us know what you're excited about working on.
Reposted by Brandon
Did you know you can use Outlines with @langchain.bsky.social?
ChatOutlines | 🦜️🔗 LangChain
This will help you getting started with Outlines chat models. For detailed documentation of all ChatOutlines features and configurations head to the API reference.
buff.ly
December 20, 2024 at 1:49 PM
Did you know you can use Outlines with @langchain.bsky.social?
Reposted by Brandon
🚨 NEW BLOG POST ALERT 🚨
We wrote a case study about .gifter, a demonstration of a simple LLM-powered web applications with structured generation (Outlines) and Flask!
It's also a tool to help you buy gifts for your loved ones, in case you need ideas.
Link: https://buff.ly/4fenrz5
We wrote a case study about .gifter, a demonstration of a simple LLM-powered web applications with structured generation (Outlines) and Flask!
It's also a tool to help you buy gifts for your loved ones, in case you need ideas.
Link: https://buff.ly/4fenrz5
December 20, 2024 at 6:59 PM
🚨 NEW BLOG POST ALERT 🚨
We wrote a case study about .gifter, a demonstration of a simple LLM-powered web applications with structured generation (Outlines) and Flask!
It's also a tool to help you buy gifts for your loved ones, in case you need ideas.
Link: https://buff.ly/4fenrz5
We wrote a case study about .gifter, a demonstration of a simple LLM-powered web applications with structured generation (Outlines) and Flask!
It's also a tool to help you buy gifts for your loved ones, in case you need ideas.
Link: https://buff.ly/4fenrz5
Reposted by Brandon
It's a new year, so we wanted to check in and see what types of content we make is the most useful.
Would you like to see more
- Blog posts (less code, more think pieces)
- Videos (deep dives + short overviews)
- Cookbooks (focused code)
- Demos (bigger projects)
Would you like to see more
- Blog posts (less code, more think pieces)
- Videos (deep dives + short overviews)
- Cookbooks (focused code)
- Demos (bigger projects)
January 2, 2025 at 6:00 PM
It's a new year, so we wanted to check in and see what types of content we make is the most useful.
Would you like to see more
- Blog posts (less code, more think pieces)
- Videos (deep dives + short overviews)
- Cookbooks (focused code)
- Demos (bigger projects)
Would you like to see more
- Blog posts (less code, more think pieces)
- Videos (deep dives + short overviews)
- Cookbooks (focused code)
- Demos (bigger projects)
Reposted by Brandon
alright pfam what AI engineering resources should we make
It's a new year, so we wanted to check in and see what types of content we make is the most useful.
Would you like to see more
- Blog posts (less code, more think pieces)
- Videos (deep dives + short overviews)
- Cookbooks (focused code)
- Demos (bigger projects)
Would you like to see more
- Blog posts (less code, more think pieces)
- Videos (deep dives + short overviews)
- Cookbooks (focused code)
- Demos (bigger projects)
January 2, 2025 at 6:49 PM
alright pfam what AI engineering resources should we make
Reposted by Brandon
What's the biggest problem you face in building AI applications?
January 6, 2025 at 4:03 PM
What's the biggest problem you face in building AI applications?
Reposted by Brandon
I have TWO big presentations on January 23rd! I will be busy.
One is LIVE in San Francisco with @dottxtai.bsky.social (me),
@neo4j.bsky.social, Modal, and Neural Magic.
The other is VIRTUAL with
@odsc.bsky.social!
ODSC: www.summit.ai?utm_campaign...
OSS AI: lu.ma/2jacrv79
One is LIVE in San Francisco with @dottxtai.bsky.social (me),
@neo4j.bsky.social, Modal, and Neural Magic.
The other is VIRTUAL with
@odsc.bsky.social!
ODSC: www.summit.ai?utm_campaign...
OSS AI: lu.ma/2jacrv79
Ai Builders
Mastering AI Agents, LLMs, RAG, and Reasoning
www.summit.ai
January 6, 2025 at 5:58 PM
I have TWO big presentations on January 23rd! I will be busy.
One is LIVE in San Francisco with @dottxtai.bsky.social (me),
@neo4j.bsky.social, Modal, and Neural Magic.
The other is VIRTUAL with
@odsc.bsky.social!
ODSC: www.summit.ai?utm_campaign...
OSS AI: lu.ma/2jacrv79
One is LIVE in San Francisco with @dottxtai.bsky.social (me),
@neo4j.bsky.social, Modal, and Neural Magic.
The other is VIRTUAL with
@odsc.bsky.social!
ODSC: www.summit.ai?utm_campaign...
OSS AI: lu.ma/2jacrv79
Reposted by Brandon
Most agent frameworks are (ironically) low-agency tools, because they take control + internals away from engineers.
Granted, they can provide some powerful abstractions.
But these abstractions are too early -- we don't know how to build AI systems. We should build from first principles.
Granted, they can provide some powerful abstractions.
But these abstractions are too early -- we don't know how to build AI systems. We should build from first principles.
Structured generation tools like Outlines are AI engineering primitives -- most agents should be using structured generation by default rather than as an afterthought.
January 3, 2025 at 5:38 PM
Most agent frameworks are (ironically) low-agency tools, because they take control + internals away from engineers.
Granted, they can provide some powerful abstractions.
But these abstractions are too early -- we don't know how to build AI systems. We should build from first principles.
Granted, they can provide some powerful abstractions.
But these abstractions are too early -- we don't know how to build AI systems. We should build from first principles.
Reposted by Brandon
Structured generation tools like Outlines are AI engineering primitives -- most agents should be using structured generation by default rather than as an afterthought.
January 3, 2025 at 4:00 PM
Structured generation tools like Outlines are AI engineering primitives -- most agents should be using structured generation by default rather than as an afterthought.
Reposted by Brandon
Are you a terrible gift giver? Would you like to use LLMs to become a slightly better gift giver?
Check out our new video!
Vid: https://buff.ly/3ZLYnep
@cameron.pfiffer.org shows off .gifter, a language model-powered gift recommendation engine. Features support for web search with Exa.
Check out our new video!
Vid: https://buff.ly/3ZLYnep
@cameron.pfiffer.org shows off .gifter, a language model-powered gift recommendation engine. Features support for web search with Exa.
How to use AI to generate gift ideas | Use a robot to become a mildly better gift giver
Description.gifter helps you find thoughtful gift ideas by analyzing descriptions of the recipient. It uses large language models to generate customized gift...
buff.ly
December 12, 2024 at 5:56 PM
Are you a terrible gift giver? Would you like to use LLMs to become a slightly better gift giver?
Check out our new video!
Vid: https://buff.ly/3ZLYnep
@cameron.pfiffer.org shows off .gifter, a language model-powered gift recommendation engine. Features support for web search with Exa.
Check out our new video!
Vid: https://buff.ly/3ZLYnep
@cameron.pfiffer.org shows off .gifter, a language model-powered gift recommendation engine. Features support for web search with Exa.
Reposted by Brandon
This is actually good to show skeptics of structured generation @dottxtai.bsky.social. Demonstrates very clearly that you can stop the model from fighting the constraints by telling it how it’s constrained, even if those constraints might seem absurd (like only using words from the King James Bible)
December 7, 2024 at 3:58 AM
This is actually good to show skeptics of structured generation @dottxtai.bsky.social. Demonstrates very clearly that you can stop the model from fighting the constraints by telling it how it’s constrained, even if those constraints might seem absurd (like only using words from the King James Bible)
Reposted by Brandon
Heya y'all, I'll be speaking at Guix Social this Thursday about Spritely! www.meetup.com/guix-social/...
I'll have a talk, but a lot of it I'm also interested in having be audience conversation about Guix, Spritely, Guile, Scheme, decentralized networks, and what we see as the future together!
I'll have a talk, but a lot of it I'm also interested in having be audience conversation about Guix, Spritely, Guile, Scheme, decentralized networks, and what we see as the future together!
Guix Social virtual meet-up - Last one of 2024!, Thu, Dec 12, 2024, 6:00 PM | Meetup
**Guix Social with talk by Christine Lemmer-Webber**
Christine will be talking about the work the Spritely Institute has been doing on bringing Guile Scheme to WASM ([Hoot!
www.meetup.com
December 10, 2024 at 6:04 PM
Heya y'all, I'll be speaking at Guix Social this Thursday about Spritely! www.meetup.com/guix-social/...
I'll have a talk, but a lot of it I'm also interested in having be audience conversation about Guix, Spritely, Guile, Scheme, decentralized networks, and what we see as the future together!
I'll have a talk, but a lot of it I'm also interested in having be audience conversation about Guix, Spritely, Guile, Scheme, decentralized networks, and what we see as the future together!
Reposted by Brandon
🏮 DEMO ALERT🏮
Introducing the Robot Santa Game, a terminal-based game that can be played by you or a language model.
This showcases how to permit a model to choose from a set of actions reliably, as is often the case with games.
Check out the demo code: https://buff.ly/49uryWK
Introducing the Robot Santa Game, a terminal-based game that can be played by you or a language model.
This showcases how to permit a model to choose from a set of actions reliably, as is often the case with games.
Check out the demo code: https://buff.ly/49uryWK
December 10, 2024 at 10:00 PM
🏮 DEMO ALERT🏮
Introducing the Robot Santa Game, a terminal-based game that can be played by you or a language model.
This showcases how to permit a model to choose from a set of actions reliably, as is often the case with games.
Check out the demo code: https://buff.ly/49uryWK
Introducing the Robot Santa Game, a terminal-based game that can be played by you or a language model.
This showcases how to permit a model to choose from a set of actions reliably, as is often the case with games.
Check out the demo code: https://buff.ly/49uryWK
Reposted by Brandon
I didn't even realize this was something we could vote on!
December 5, 2024 at 4:29 PM
I didn't even realize this was something we could vote on!
Reposted by Brandon
YouTube: https://www.youtube.com/watch?v=csw6TVfzBcw
Code: https://github.com/dottxt-ai/demos/tree/main/logs
Code: https://github.com/dottxt-ai/demos/tree/main/logs
December 5, 2024 at 5:03 PM
Reposted by Brandon
🏮 New YouTube video! 🏮
We experimented with a log monitoring system. Spin up the agent and it'll monitor your logs for any potential issues -- it works with webserver logs like nginx or Apache, Linux system logs, etc.
We experimented with a log monitoring system. Spin up the agent and it'll monitor your logs for any potential issues -- it works with webserver logs like nginx or Apache, Linux system logs, etc.
December 5, 2024 at 5:03 PM
🏮 New YouTube video! 🏮
We experimented with a log monitoring system. Spin up the agent and it'll monitor your logs for any potential issues -- it works with webserver logs like nginx or Apache, Linux system logs, etc.
We experimented with a log monitoring system. Spin up the agent and it'll monitor your logs for any potential issues -- it works with webserver logs like nginx or Apache, Linux system logs, etc.
Reposted by Brandon
This is an important distinction -- I recommend reading this if you use some kind of tool to structure output.
There's often a lot of confusion about what structured generation actually is. Brief thread.
Structured generation, also called structured output or constrained decoding, is always correctly formatted. The model literally cannot fail to output the format you specify.
Structured generation, also called structured output or constrained decoding, is always correctly formatted. The model literally cannot fail to output the format you specify.
December 5, 2024 at 4:57 PM
This is an important distinction -- I recommend reading this if you use some kind of tool to structure output.
Reposted by Brandon
🏮 New YouTube video! 🏮
We experimented with a log monitoring system. Spin up the agent and it'll monitor your logs for any potential issues -- it works with webserver logs like nginx or Apache, Linux system logs, etc.
youtu.be/csw6TVfzBcw
We experimented with a log monitoring system. Spin up the agent and it'll monitor your logs for any potential issues -- it works with webserver logs like nginx or Apache, Linux system logs, etc.
youtu.be/csw6TVfzBcw
Creating a Structured AI Log Analysis System with Python & LLMs
YouTube video by dottxt
youtu.be
December 5, 2024 at 5:08 PM
🏮 New YouTube video! 🏮
We experimented with a log monitoring system. Spin up the agent and it'll monitor your logs for any potential issues -- it works with webserver logs like nginx or Apache, Linux system logs, etc.
youtu.be/csw6TVfzBcw
We experimented with a log monitoring system. Spin up the agent and it'll monitor your logs for any potential issues -- it works with webserver logs like nginx or Apache, Linux system logs, etc.
youtu.be/csw6TVfzBcw
Reposted by Brandon
Link to a recording of my talk: www.youtube.com/live/x94JRyz...
YouTube
Share your videos with friends, family, and the world
www.youtube.com
November 25, 2024 at 9:07 PM
Link to a recording of my talk: www.youtube.com/live/x94JRyz...
Reposted by Brandon
New video! @cameron.pfiffer.org talks to our computational linguist Daniel Quernheim.
Learn what context free grammars are, and how to make JSON where every string has to start with the letter A.
youtu.be/rMHdpo_D9m0?...
Learn what context free grammars are, and how to make JSON where every string has to start with the letter A.
youtu.be/rMHdpo_D9m0?...
Understanding Context-Free Grammars: An Interview with .txt's Daniel Quernheim!
YouTube video by dottxt
youtu.be
November 26, 2024 at 4:47 PM
New video! @cameron.pfiffer.org talks to our computational linguist Daniel Quernheim.
Learn what context free grammars are, and how to make JSON where every string has to start with the letter A.
youtu.be/rMHdpo_D9m0?...
Learn what context free grammars are, and how to make JSON where every string has to start with the letter A.
youtu.be/rMHdpo_D9m0?...
Reposted by Brandon
Check out our new YouTube video. We're trying out kind of an interview format, so let me know if you love/hate this
New video! @cameron.pfiffer.org talks to our computational linguist Daniel Quernheim.
Learn what context free grammars are, and how to make JSON where every string has to start with the letter A.
youtu.be/rMHdpo_D9m0?...
Learn what context free grammars are, and how to make JSON where every string has to start with the letter A.
youtu.be/rMHdpo_D9m0?...
Understanding Context-Free Grammars: An Interview with .txt's Daniel Quernheim!
YouTube video by dottxt
youtu.be
November 26, 2024 at 4:47 PM
Check out our new YouTube video. We're trying out kind of an interview format, so let me know if you love/hate this
Reposted by Brandon
lesson: if you care about the performance of something, you gotta run your own benchmarks
A new paper, "Let Me Speak Freely" has been spreading rumors that structured generation hurts LLM evaluation performance.
Well, we've taken a look and found serious issue in this paper, and shown, once again, that structured generation *improves* evaluation performance!
Well, we've taken a look and found serious issue in this paper, and shown, once again, that structured generation *improves* evaluation performance!
November 22, 2024 at 8:07 AM
lesson: if you care about the performance of something, you gotta run your own benchmarks