Our great sponsors
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
GitLab team member here. Thanks for flagging.
Our web team is working to resolve this issue here: https://gitlab.com/gitlab-com/marketing/digital-experience/b...
Notice how it even included a comment referencing a specific datasheet!
This driver is hardly "famous" or even "notable", because those aren't things LLMs understand. The prompt simply contains enough context to be distinctive and the sht21.c is an old, stable driver in each of the many kernel trees included in its training set.
Regurgitation isn't a particularly rare thing with LLMs, most cases just aren't this obvious.
[1] https://github.com/torvalds/linux/blob/c6b0271053e7a5ae57511...
GitLab team member here. Thanks for your feedback.
> But IMO there are plenty of other places to add real value across the GitLab product with AI/ML features.
True, and after starting with ML experiments, the product and engineering teams have been working on new features for entire DevOps lifecycle. All AI workflows on the DevSecOps platforms are described in the GitLab Duo announcement blog post https://about.gitlab.com/blog/2023/06/22/meet-gitlab-duo-the... and website https://about.gitlab.com/gitlab-duo/
I'll share a few highlights that I am personally excited about
- Explain and help fix security vulnerabilities. From my personal experience, I often find CVEs hard to read, especially when I am not the author of the code to fix. Getting help from AI can reduce entry barriers and make development for efficient. Security is everyone's responsibility these days. This follows the AI assisted feature to explain code in general. "What does this magic loop with memcpy do?" might not stay magic anymore, easing the path to code refactoring, improving performance, and reduce the resource usage footprint.
- Summarize issue comments. Feature proposals or bug analysis can have long comment threads that require reading time. AI will help get the gist and better contribute to what has been discussed.
- Summarize MR changes, to avoid reading long change diffs. This helps with faster (code) review cycles. I tested it this week with an MR for our handbook in https://gitlab.com/gitlab-com/www-gitlab-com/-/merge_request...
I'd also like to see AI helping fix CI/CD pipelines fast. Proposal in https://gitlab.com/gitlab-org/gitlab/-/issues/386863 I shared some thoughts in a new talk "Observability for Efficient DevSecOps Pipelines", slides in https://go.gitlab.com/VDAvMw (GitLab blog post coming soon, https://gitlab.com/gitlab-com/www-gitlab-com/-/issues/34296)
Additionally, I learned some new ideas at Cloudland last week, regarding product owner requirements list verification, and end-to-end test automation with AI. Need to create feature proposals :-)
> As a longtime GitLab user (and onetime contributor!),
Thanks for contributing. I'd like to invite you to share your ideas about AI features across the platform :)
When you look at the DevOps lifecycle (image in https://about.gitlab.com/gitlab-duo/) from plan/manage to create, verify, secure, package, release, deploy, monitor, govern - where do you see yourself, and where do you spend the most time in?
Second question: Which process feels the most inefficient? After identifying answers to the questions, please check the AI features https://docs.gitlab.com/ee/user/ai_features.html and/or open new feature proposals for GitLab https://gitlab.com/gitlab-org/gitlab/-/issues/new?issuable_t... You can tag @dnsmichi so I can engage with your ideas. Thanks!
GitLab team member here. Thanks for your feedback.
> But IMO there are plenty of other places to add real value across the GitLab product with AI/ML features.
True, and after starting with ML experiments, the product and engineering teams have been working on new features for entire DevOps lifecycle. All AI workflows on the DevSecOps platforms are described in the GitLab Duo announcement blog post https://about.gitlab.com/blog/2023/06/22/meet-gitlab-duo-the... and website https://about.gitlab.com/gitlab-duo/
I'll share a few highlights that I am personally excited about
- Explain and help fix security vulnerabilities. From my personal experience, I often find CVEs hard to read, especially when I am not the author of the code to fix. Getting help from AI can reduce entry barriers and make development for efficient. Security is everyone's responsibility these days. This follows the AI assisted feature to explain code in general. "What does this magic loop with memcpy do?" might not stay magic anymore, easing the path to code refactoring, improving performance, and reduce the resource usage footprint.
- Summarize issue comments. Feature proposals or bug analysis can have long comment threads that require reading time. AI will help get the gist and better contribute to what has been discussed.
- Summarize MR changes, to avoid reading long change diffs. This helps with faster (code) review cycles. I tested it this week with an MR for our handbook in https://gitlab.com/gitlab-com/www-gitlab-com/-/merge_request...
I'd also like to see AI helping fix CI/CD pipelines fast. Proposal in https://gitlab.com/gitlab-org/gitlab/-/issues/386863 I shared some thoughts in a new talk "Observability for Efficient DevSecOps Pipelines", slides in https://go.gitlab.com/VDAvMw (GitLab blog post coming soon, https://gitlab.com/gitlab-com/www-gitlab-com/-/issues/34296)
Additionally, I learned some new ideas at Cloudland last week, regarding product owner requirements list verification, and end-to-end test automation with AI. Need to create feature proposals :-)
> As a longtime GitLab user (and onetime contributor!),
Thanks for contributing. I'd like to invite you to share your ideas about AI features across the platform :)
When you look at the DevOps lifecycle (image in https://about.gitlab.com/gitlab-duo/) from plan/manage to create, verify, secure, package, release, deploy, monitor, govern - where do you see yourself, and where do you spend the most time in?
Second question: Which process feels the most inefficient? After identifying answers to the questions, please check the AI features https://docs.gitlab.com/ee/user/ai_features.html and/or open new feature proposals for GitLab https://gitlab.com/gitlab-org/gitlab/-/issues/new?issuable_t... You can tag @dnsmichi so I can engage with your ideas. Thanks!