New on LowEndTalk? Please Register and read our Community Rules.
All new Registrations are manually reviewed and approved, so a short delay after registration may occur before your account becomes active.
All new Registrations are manually reviewed and approved, so a short delay after registration may occur before your account becomes active.
How do you think ChatGPT API could be utilized in server management? What effects on pricing?
Any ideas how stuff can be automated in this area? Asking it to write Bash or Docker scripts?
Would it make sysadmins redundant?
Thanked by 1default
Would increase of popularity of ML methods cause an increase in VPS prices esp. GPU-based offerings?
- Your opinion?28 votes
- Yes10.71%
- No35.71%
- It actually makes VPS offerings cheaper17.86%
- Who knows? Let's see how market behaves35.71%
Comments
The poll and post are two very different questions.
Related to the poll, I think it'll increase demand for GPU power which means the hosted GPU market will be growing. With supply being able to catch up I think we'll see more GPU offerings coming into the market soon beyond the current pool of vendors therefore increasing competition and bringing down the unit cost of GPU power. Therefore, I think it's going to actually make GPU-powered VPS prices much cheaper in 3-5 years from now.
I say 3-5 years because while I can make a ML model a lot of people also can't make their own bespoke ML models and instead most will use off-the-shelf framework or solutions (by this I mean tools to build your own ML solutions without having to know about programming). So I don't think there are "good enough" ML products that are self-hosted-friendly and are just "plug-and-play". I think this space needs to mature more in order to increase that demand for self-hosted GPU VPSes instead of hosted solutions (again, like ChatGPT). I know there are open source models like Stable Diffusion and other voice models but I don't think it's that user friendly still. It's not like installing LibreNMS or Netbox. I'd like to also ping @lentro because his company TensorFlow operate within this space and offer, imho, one of the best value for cost/power ratio.
Related to implementation of these tools...
It's my opinion that these outputs are flashy but aren't ready for immediate implementation. They're good as a "first stab" but you need someone who knows the material and knows the matter to actually review it and edit it because there are so many wrong answers ML models like ChatGPT gives out that "looks right" but really aren't. Maybe an element of equifinality. Even look at Github Copilot. So until this concern is reduced or minimized and we can build more confidence to the output of the results, it'll simply be a tool to help optimize someone who's already a developer who just needs to code faster but will be misleading for others.
I'm sure others who are also exposed to model building can comment with their own opinion. I'm not saying it's bad, it's just another tool in a model builder's toolkit that we can use. But I don't think it's as matured or generalized as people think it is. At the end of the day, most ML models are advanced empirical models. So many theories and approaches to empirical modeling have already been a concept and a thing since the early 60s or so. It's just that we now have the resources/power/affordable computing capability to actually explore this space faster than we had before.
TLDR: I think it'll get cheaper. I think it'll just speed up the workflow for people who know what they're doing but will be hit-or-miss for others. I'm thinking something similar to Github CoPilot though.
Through answer @HalfEatenPie , thanks
As an AI language model, ChatGPT can provide assistance to server management tasks by providing natural language processing and generation capabilities. Here are a few ways in which ChatGPT API could be utilized in server management:
Chat-based server management: ChatGPT API can be integrated into chatbots to help manage servers through a conversational interface. Users can ask questions or give commands in natural language, and ChatGPT can provide responses or execute the necessary tasks.
Scripting automation: ChatGPT can be used to generate Bash or Docker scripts based on user inputs or system parameters. This could be useful for automating repetitive tasks or standardizing configurations across multiple servers.
Troubleshooting assistance: ChatGPT can help troubleshoot issues by analyzing server logs, identifying common problems, and suggesting solutions.
Regarding pricing, it depends on how the ChatGPT API is used and integrated into server management tools. For example, if ChatGPT is used as part of a commercial server management tool, the tool's pricing may be impacted. However, if ChatGPT is used to develop a custom in-house server management solution, there may be minimal or no impact on pricing.
In terms of automation, ChatGPT can certainly help automate some server management tasks, but it's unlikely to make sysadmins redundant. While AI and automation can assist with routine tasks, sysadmins still play a critical role in managing complex systems, troubleshooting issues, and making strategic decisions. Rather than replacing sysadmins, ChatGPT can augment their skills and help them work more efficiently.
Generated by ChatGPT
Generated by ChatGPT and the answer is different:
There are various methods to automate tasks in this area, such as leveraging Bash or Docker scripts. However, the potential impact on the role of sysadmins is a complex issue. While automation can improve efficiency and reduce the need for manual labor in certain areas, it can also create new opportunities for sysadmins to focus on higher-level functions like system design and strategic planning. The net effect on sysadmins is ultimately dependent on the specifics of the automation used and the overall goals of the organization.
Regarding the utilization of ChatGPT API in server management, there is potential for it to be utilized in several ways. For example, the API could be leveraged to analyze log files and detect potential issues before they escalate. It could also be utilized to provide real-time insights into server performance and to suggest optimizations to improve efficiency. However, the specific use cases and benefits of using ChatGPT API in server management would depend on the context and goals of the organization.
As for pricing, the impact of using ChatGPT API on server management costs would depend on various factors, such as the size and complexity of the infrastructure, the amount of automation already in place, and the specifics of how the API is utilized. Generally, leveraging the API for automation purposes could lead to cost savings over time, but it's essential to carefully consider the potential benefits and costs before making any significant changes to server management strategies.
No, pizza is not a fruit. Pizza is typically considered a type of savory food that is made with a dough crust, tomato sauce, cheese, and various toppings such as vegetables, meats, and herbs. While tomatoes are often used in the sauce on a pizza, they are technically a fruit, but that does not make pizza itself a fruit.
Generated by ChatGPT