As someone who's always tweaking front-end projects and looking for feedback, code reviews can turn into a total time suck (especially when you're solo or juggling sprints.) So I decided to check out @EntelligenceAI, and these are my honest first impressions. 🤓 Spoiler: It's not another Copilot clone.

🚀 Launching at @AGIHouseSF today @EntelligenceAI now has full integrations with Slack and Google Calendar! No more wasting time keeping up with Slack threads or repeating updates in project syncs, standups, and 1:1s. Streamline your engineering with entelligence.ai!

Guiding Language Models of Code with Global Context using Monitors paper page: huggingface.co/papers/2306.1… Language models of code (LMs) work well when the surrounding code in the vicinity of generation provides sufficient context. This is not true when it becomes necessary to use types or functionality defined in another module or library, especially those not seen during training. LMs suffer from limited awareness of such global context and end up hallucinating, e.g., using types defined in other files incorrectly. Recent work tries to overcome this issue by retrieving global information to augment the local context. However, this bloats the prompt or requires architecture modifications and additional training. Integrated development environments (IDEs) assist developers by bringing the global context at their fingertips using static analysis. We extend this assistance, enjoyed by developers, to the LMs. We propose a notion of monitors that use static analysis in the background to guide the decoding. Unlike a priori retrieval, static analysis is invoked iteratively during the entire decoding process, providing the most relevant suggestions on demand. We demonstrate the usefulness of our proposal by monitoring for type-consistent use of identifiers whenever an LM generates code for object dereference. To evaluate our approach, we curate PragmaticCode, a dataset of open-source projects with their development environments. On models of varying parameter scale, we show that monitor-guided decoding consistently improves the ability of an LM to not only generate identifiers that match the ground truth but also improves compilation rates and agreement with ground truth. We find that LMs with fewer parameters, when guided with our monitor, can outperform larger LMs. With monitor-guided decoding, SantaCoder-1.1B achieves better compilation rate and next-identifier match than the much larger text-davinci-003 model.

This is great move by the @EntelligenceAI Instant code feedback while you're vibing in your IDE? That’s a game-changer. Excited to try this out in VS Code and Cursor. Dev workflows just got smarter.

Me: Commiting My Agent Squad (@coderabbitai, Google Assistant, @EntelligenceAI) Jesus f christ what's this shitty code I need to review😂

Happy Halloween all! 🎃 👻 Unclear how redesigning our landing page in Halloween theme got to the top of the priority list.... but we did it anyway more of this little guy coming up for the entire holiday season :)

We now have a chat-with-your docs! Go check it out: assistant-ui.com/docs (Desktop-only) The best part? You can even ask it about undocumented APIs! 🤯 Made possible thanks to @EntelligenceAI, which has read our source code, PRs, issues and even Discord threads!

Team @EntelligenceAI is presenting at ELC today! If you’re at the conference, come watch our presentation in room 4 at 1:30 pm today!! We’ll be showcasing how we’ve been building the foundational engineering context awareness and planning platform that powers our onboarding agents, code review, code chat and more!

|￣￣￣￣￣￣￣￣￣￣￣￣￣￣| !Push To Production On Friday| |＿＿＿＿＿＿＿＿＿＿＿＿＿＿| \ (•◡•) / \ / —— | | |_ |_

Even if AI can write perfect code, engineering organizations will still be as inefficient. At Entelligence, it's our goal to solve that. Excited to have won 2nd at the @agihouse_org Enterprise AI Hackathon sponsored by @AnthropicAI and @coatuemgmt! 📷