Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Show HN: Anyshift.io – Terraform "Superplan"

app.anyshift.io

Post reply on HN
Print view View original

11–20 of 47 posts

Re: Show HN: Anyshift.io – Terraform "Superplan"

#13

Post by emmtold »

fasten wrote: post #7
emmtold wrote: post #4

Cool post, thank you for sharing, it could be a useful use case indeed. You mention AI-generated code causing dependency issues. Are there plans to integrate AI-driven recommendations?

Thanks for the feedback! We already use AI in the PR to explain whats happening and the best practices to adopt. As for the code remediation part: most LLMs fail to generate the right IaC code thats adapted to your infra because they miss its general context (config, dependencies..). We are building first the deterministic part (the context) and once we have the context our plan is to add the fix/recommendation in th…

Ok focusing on context makes sense but I’d challenge the idea that LLMs inherently fail without it. Some teams have used fine-tuned models or hybrid workflows with partial context to generate useful IaC snippets

Re: Show HN: Anyshift.io – Terraform "Superplan"

#15

Post by anAiguy »

fasten wrote: post #7
emmtold wrote: post #4

Cool post, thank you for sharing, it could be a useful use case indeed. You mention AI-generated code causing dependency issues. Are there plans to integrate AI-driven recommendations?

Thanks for the feedback! We already use AI in the PR to explain whats happening and the best practices to adopt. As for the code remediation part: most LLMs fail to generate the right IaC code thats adapted to your infra because they miss its general context (config, dependencies..). We are building first the deterministic part (the context) and once we have the context our plan is to add the fix/recommendation in th…

How will you be checkiing the quality of the AI recommendations in the your PR. Do you think that using different model ( chatgpt, claude,gemin, qwen) to challenge the recommendation made by another AI could help ?

Re: Show HN: Anyshift.io – Terraform "Superplan"

#19

Post by fasten »

emmtold wrote: post #13
fasten wrote: post #7

Earlier quoted context omitted.

Thanks for the feedback! We already use AI in the PR to explain whats happening and the best practices to adopt. As for the code remediation part: most LLMs fail to generate the right IaC code thats adapted to your infra because they miss its general context (config, dependencies..). We are building first the deterministic part (the context) and once we have the context our plan is to add the fix/recommendation in th…

Ok focusing on context makes sense but I’d challenge the idea that LLMs inherently fail without it. Some teams have used fine-tuned models or hybrid workflows with partial context to generate useful IaC snippets

Agreed 100%. LLMs are doing solid job at generating IaC but in a context where the person who use them knows what he/she's doing. In our case, remediaiton means an extra level of trust, where your infra is already super sensitive.

Re: Show HN: Anyshift.io – Terraform "Superplan"

#20

Post by benjipick »

fasten wrote: post #8
benjipick wrote: post #5

sounds cool but how do you prevent it from false positives? What’s the accuracy rate so far?

In our Pull Request bot, we provide more information with a clear sumup of whats gonna be impacted. One of our next feature is to configure what type of information is more critical to you: by type of resources, owner (git blame) and tags. Do you have one that you would prefer in particular ?

I guess by type of resources but also env would be interesting. I don't care on most of the impact of my dev end tbh.
Post reply on HN