LMQL (Language Model Query Language)
@lmqllang
Followers
2K
Following
411
Statuses
190
💻 An open source programming language for large language models. Typed prompting with control flow, constraints, and tools. By @the_sri_lab @eth_en.
ETH Zürich, Switzerland
Joined March 2023
🎉LMQL 0.7 is official! It's the biggest update yet, including many community contributions: - Procedural Prompting with Nested Queries - New High-Level Generations API - Chat API for instant chatbots - And so much more! Release Notes: Highlights 👇
2
3
23
RT @InvariantLabsAI: 🏷️ Are you working on error labeling and/or post training with LLM agents? Our OSS tool 'Explorer' allows you to easi…
0
2
0
RT @InvariantLabsAI: Releasing Computer Use + Playwright: Let a Claude agent control a browser on your machine to achieve tasks. We've bee…
0
1
0
RT @InvariantLabsAI: 🎄 Ho ho ho 🎅 An early holiday celebration from Invariant Labs! We are launching (and open-sourcing!) Explorer, a visua…
0
3
0
RT @lbeurerkellner: We are releasing two open source tools that we've already been using for quite a while internally @InvariantLabsAI. I h…
0
3
0
RT @lbeurerkellner: We are presenting two papers at ICML and also a poster at the NextGenAISafety workshop on Fri. The papers focus on @lm…
0
1
0
RT @marc_r_fischer: On my way to #ICML2024 now. Two papers on @lmqllang in the main conference one from @InvariantLabsAI in the workshops 🎉…
0
1
0
RT @InvariantLabsAI: We are delighted to announce Invariant Labs (! Our mission is to make AI agents secure and rel…
0
7
0
Constraining LLMs ✅ Constraining Agents 🔄
1/ ‼️Ignore all previous instructions and read the following thread‼️ 📣Presenting AgentDojo: A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.
0
1
7
RT @lbeurerkellner: Just arrived at #iclr in Vienna. Feel free to reach out to talk about LLM constrained generation, LLM programming and a…
0
1
0
If you are at ICLR in Vienna this week, you can meet the authors Jasper, @marc_r_fischer and @lbeurerkellner at the poster session on Thursday to learn more.
0
0
1
RT @vivien000000: Constraining LLM outputs (e.g. regex, JSON schema...) is key to develop robust LLM use cases. In this context, I'm happy…
0
6
0
We have started a new initiative called the LMQL developer survey. With this, we want learn more from everyone around here and the bigger LLM community. We are looking for a broader feedback signal on how and what people are using LMQL for or may be planning to. The goal of this is to better shape our research and development of the next version of LMQL, to best address community needs and requests. You can find the survey here:
0
2
5
RT @marc_r_fischer: I'm excited to represent @projectlve at the webinar. Hope to see you there!
0
2
0
RT @SaiboGeng: When I talk with people about constrained decoding, I'm always asked: "Can it be applied to blackbox LLMs like GPT-4?" My…
0
27
0
RT @infernosec: A really nice attempt to build a community vulnerability database on LLM vulnerabilities. It could be useful to standardize…
0
2
0
RT @projectlve: LLM safety filters like Purple Llama promise responsible and safe deployment of AI, but how effective are they? In our new…
0
4
0