Sign in

Rémi

@remilouf.bsky.social
1.6K followers 502 following 22 posts

CEO & co-founder at .txt. I wander.

PostsRepliesMedia
Reposted by Rémi
.txt @dottxtai.bsky.social · 13/07/2025
We changed the way we handle multimodal inputs in Outlines. Most libraries will give the prompt a special role, separate it from the other inputs. We don’t anymore.
061
Reposted by Rémi
Clelia Astra Bertelli @cle-does-things.bsky.social · 12/07/2025
📝 I have been meaning to write this for a while now, but after reading @remilouf.bsky.social's post on the potential of structured generation for LLMs and a post on SerDes debt deriving from Pydantic usage, I decided I should not wait any longer. So here is my new blog post:
121
Reposted by Rémi
DPB @deepybee.bsky.social · 19/02/2025
🦀 Do you like Rust? 🇫🇷 Do you like Paris? Then you'll love the conference, Rust In Paris, that my colleague Yvan Sraka is delivering his talk, Beyond Procedural Macros: A Trait-Based Framework for Bindgen, at next month! www.rustinparis.com
033
Reposted by Rémi
samudranb.bsky.social @samudranb.bsky.social · 24/01/2025
This was absolutely my favorite talk from today! Love it / scared of it
133
Reposted by Rémi
.txt @dottxtai.bsky.social · 11/12/2024
Outlines 0.1.9 release is out! Small release, but some highlights: - First contribution by @chicham! - You can now use enums in outlines.generate.choice - Compilation time improvements. - Using the rust-native JSON-schema to regex, rather than the Python implementation
0102
Reposted by Rémi
Chris McMaster @rheumai.com · 07/12/2024
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)
074
Rémi @remilouf.bsky.social · 28/11/2024
HF has done, and keeps doing, a lot of good in the AI ecosystem. I’ll die on this hill.
2403
Rémi @remilouf.bsky.social · 28/11/2024
More insults under an apology post on Bluesky than under any outrageous post on Twitter. Be the change you want to see in the world or something like that.
0161
Reposted by Rémi
Cameron @cameron.stream · 26/11/2024
Check out our new YouTube video. We're trying out kind of an interview format, so let me know if you love/hate this
0113
Rémi @remilouf.bsky.social · 28/11/2024
Looking at the comments of this one, I think this is actually the Bad Place
141
Rémi @remilouf.bsky.social · 27/11/2024
The comments on this are unnecessarily hateful. I thought this place was better.
3120
Rémi @remilouf.bsky.social · 24/11/2024
Give @dottxtai.bsky.social a follow for quality structured generation content!
042
Reposted by Rémi
.txt @dottxtai.bsky.social · 21/11/2024
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!
412323
Rémi @remilouf.bsky.social · 22/11/2024
The "Let Me Speak Freely" got way too much traction too easily, despite a few serious issues. Well aware of Brandolini's law we published a thorough rebuttal of the main conclusion, highlighted the key methodological flaws and taught a few things in the process. Hope you enjoy it!
171
Reposted by Rémi
.txt @dottxtai.bsky.social · 21/11/2024
Our new blog post is out! @willkurt.bsky.social provides a rebuttal for a reasonably well known paper which concluded that structured generation with LLMs always resulted in worse performance. We do not find the same thing. blog.dottxt.co/say-what-you...
A graph showing that structured generation performs better than unstructured generation.
1137
Reposted by Rémi
Cameron @cameron.stream · 20/11/2024
Y'ALL this is my first @dottxtai.bsky.social video to break 1k views!!!!! youtu.be/_SK2sO0_DEY?...
youtu.be
Build an AI receipt scanner with vision language models!
YouTube video by dottxt
1143
Rémi @remilouf.bsky.social · 20/11/2024
What’s the best LLM observability tool today?
241
Rémi @remilouf.bsky.social · 20/11/2024
👋 New followers I’m Rémi, co-founder and CEO of @dottxtai.bsky.social. We do structured generation with LLM, which means we are able to enforce constraints on the output (regex, JSON Schema, Grammar) during inference time. It’s very cool. dottxt.co
dottxt.co
dottxt - make ai speak computer
1212
Rémi @remilouf.bsky.social · 20/11/2024
I wake up every day with 100 new followers now. The Starter Packs were a brilliant idea ✨
240
Reposted by Rémi
.txt @dottxtai.bsky.social · 19/11/2024
Hello Bluesky! We're here now. Wonderful to be in the Good Place. We'll be posting demos, interesting tidbits, and boosting cool AI stuff on here. dottxt.co
dottxt.co
dottxt - make ai speak computer
094
Reposted by Rémi
Joey Rudoler @jrudoler.bsky.social · 11/11/2024
(Reposting from X) I did a tiny side project: a program that automatically generates a properly formatted .ics file from a text description (e.g. copy/paste an email) using an LLM, and imports it to your favorite calendar app! Structured generation is cool -- shoutout @remilouf.bsky.social and .txt
252
Rémi @remilouf.bsky.social · 07/11/2024
📊 One weird trick to parse earnings reports! Wall Street analysts HATE this! Use LLMs to convert messy SEC filings into clean CSV data using structured generation. The one weird trick? Convert your HTML to markdown + use Outlines. Link below 👇
140
Rémi @remilouf.bsky.social · 05/11/2024
To celebrate the release of @huggingface.bsky.social’s new SmolLM2 series of models we created a fun demo: the Bunny B1. The Bunny B1 shows how a small device using a SmolLM2 model + Outlines can consistently map natural language requests to the correct app! Check it out in this gif!
150
Rémi @remilouf.bsky.social · 02/11/2024
Week-end read
140
Reposted by Rémi
Daniel van Strien @danielvanstrien.bsky.social · 01/11/2024
Outlines is a great library for structured generation for LLMs/VLMs, which is really helpful for many use cases. @remilouf.bsky.social and the team are working towards a 1.0.0 release with an API that looks very nice, in my opinion.
Screenshot of a tweet showing the following text: 

We are working towards Outlines 1.0.

We unfortunately have to refactor the user interface to make the library more flexible (it's worth it). What do you think of the following?

and a screenshot of some code examples
071
Reposted by Rémi
Karen Ullrich (s/h) @karen-ullrich.bsky.social · 30/10/2024
Phan et al, found a method to mitigate some of the tokenization problems Karpathy mentioned by projecting tokens into byte space. The key to their method is to develop a map between statistically equivalent token and byte-level models.
031
Rémi @remilouf.bsky.social · 27/10/2024
Ok what did I miss
030