Continue

Continue Newsletter: Monthly Updates

Continue Newsletter: Monthly Updates

May 2024 Updates Continue Updates 🌠 Our open-source VS Code and JetBrains extensions crossed 10K stars on GitHub 🦙 Llama 3 8B and 70B, which match the capabilities of models of significantly larger size, and Gemini 1.5 Pro with a 1,000,000 token context length are available in Continue 🤠 Continue&

How to measure the impact of AI software development systems

How to measure the impact of AI software development systems

Empowering your developers with an AI software development system, which they can use to automate more tasks in their job, will improve engineering outcomes and quality of life for developers at your organization. For example, ML-enhanced code completion was shown to improve developer productivity at Google and GitHub. Below we

How can you improve the code suggestions you get from LLMs?

How can you improve the code suggestions you get from LLMs?

Josh Collinsworth wrote a post titled “I worry our Copilot is leaving some passengers behind” a couple weeks ago, and I can’t stop thinking about it, especially this section in particular: "Why should we just accept that LLM tools not only fail to at least give us the

LLMs are helpful with Python, but what about all of the other programming languages?

LLMs are helpful with Python, but what about all of the other programming languages?

Recently, many folks have been claiming that their LLM is the best at coding. Their claims are typically based off of self-reported evaluations on the HumanEval benchmark. But when you look into that benchmark, you realize that it only consists of 164 Python programming problems. This led me down a

We’ve raised $2.1M to make building software feel like making music

We’ve raised $2.1M to make building software feel like making music

We believe that large language models (LLMs) present a new opportunity to make building software feel like making music. Developers excel when their work feels like strumming a guitar at a campfire, singing along to the radio, or experimenting with beats in GarageBand—not when it’s a slog through

What are the accuracy limits of codebase retrieval?

What are the accuracy limits of codebase retrieval?

To automatically determine the most important context from your codebase, we've just released v1 of Continue's codebase retrieval feature. You can ask questions like “where do I add a new endpoint to the server?”, “what scripts are used to build this project?”, or “where do I

How to use a Large Language Model while coding

How to use a Large Language Model while coding

Why use an LLM while coding For the first time ever, it’s possible to build software without writing any code yourself, though if taken literally this is currently limited to small “from-scratch” projects. On the other end of the spectrum, LLMs are often too slow to use for the

Is it still necessary to tune an LLM preset? Tracing the history of temperature, penalty, and sampling schemes

Is it still necessary to tune an LLM preset? Tracing the history of temperature, penalty, and sampling schemes

🧪TL;DR: The preset includes knobs that you can use to shape LLM behavior when the responses are not like you want. They were more necessary when LLMs weren't so large but can still be important today. Introduction These days, every large language model (LLM) roughly comes with

An introduction to code LLM benchmarks for software engineers

An introduction to code LLM benchmarks for software engineers

Benchmarks are used by researchers to evaluate and compare the relative performance of LLMs. Although there is no replacement for trying out LLMs yourself while coding to figure out which one works best for you, benchmarks and popularity rankings can help determine which LLMs are worth trying. As of October

How to deploy an open-source code LLM for your dev team

How to deploy an open-source code LLM for your dev team

Deploying an open-source code LLM for your team right can be difficult. You need to: * find a deployment method that is private and secure enough * consistently get the GPUs you need when you need them * make sure your LLM of choice works reliably on those GPUs * do it while keeping

What LLM to use? A perspective from the DevAI space

What LLM to use? A perspective from the DevAI space

With how fast things are moving in the DevAI space, a shorthand for the community of developers building software with the help of large language models (LLMs), it can be challenging to figure out which model to use. We started this repository based on our experiences as part of the

Continue: Enhancing my software development with AI assistance (Community Post)

Continue: Enhancing my software development with AI assistance (Community Post)

This is a guest post on the Continue Blog by Tommy Ubongabasi, a full-stack developer from Uyo, Nigeria. He has been one of our most enthusiastic early contributors. We are excited for him to share his experience as part of the Continue community. How I got started with Continue Recently

It’s time to collect data on how you build software

It’s time to collect data on how you build software

The next generation of developers use LLMs instead of Google + Stack Overflow The next generation of developers is replacing Google + Stack Overflow with Large Language Models (LLMs), just as the generation before replaced reference manuals with Google + Stack Overflow. The organizations that retain and attract developers through this transition will