Not sure I understand the joy some of you get at the THOUGHT of jobs being eliminated.
Is it a wrap for Software Engineers? Devin autonomous AI software engineer...
- Thread starter KingDanz
- Start date
Json
Superstar
I’m just playing
The situation is funny only in the sense that ironically a lot of times these tech innovations are targeted at unskilled labor.
Productivity monitors, drones delivery, robot kitchen, etc. so the fact the innovation eliminates many of the people making it is crazy.
AI : Mere days after software agent Devin is released, an open-source alternative, SWE-agent, is almost as good.
github.com
SWE-agent turns LMs (e.g. GPT-4) into software engineering agents that can fix bugs and issues in real GitHub repositories.
On the full SWE-bench test set, SWE-agent resolves 12.29% of issues, achieving the state-of-the-art performance on the full test set.
We accomplish these results by designing simple LM-centric commands and feedback formats to make it easier for the LM to browse the repository, view, edit and execute code files. We call this an Agent-Computer Interface (ACI) and build the SWE-agent repository to make it easy to iterate on ACI design for repository-level coding agents.
Just like how typical language models requires good prompt engineering, good ACI design leads to much better results when using agents. As we show in our paper, a baseline agent without a well-tuned ACI does much worse than SWE-agent.
SWE-agent contains features that we discovered to be immensly helpful during the agent-computer interface design process:
@misc{yang2024sweagent,<br> title={SWE-agent: Agent Computer Interfaces Enable Software Engineering Language Models}, <br> author={John Yang and Carlos E. Jimenez and Alexander Wettig and Shunyu Yao and Karthik Narasimhan and Ofir Press},<br> year={2024},<br>}<br>
GitHub - princeton-nlp/SWE-agent: [NeurIPS 2024] SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges.
[NeurIPS 2024] SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challen...
github.com
About
SWE-agent: Agent Computer Interfaces Enable Software Engineering Language Models
Overview
SWE-agent turns LMs (e.g. GPT-4) into software engineering agents that can fix bugs and issues in real GitHub repositories.On the full SWE-bench test set, SWE-agent resolves 12.29% of issues, achieving the state-of-the-art performance on the full test set.
Agent-Computer Interface (ACI)
We accomplish these results by designing simple LM-centric commands and feedback formats to make it easier for the LM to browse the repository, view, edit and execute code files. We call this an Agent-Computer Interface (ACI) and build the SWE-agent repository to make it easy to iterate on ACI design for repository-level coding agents.Just like how typical language models requires good prompt engineering, good ACI design leads to much better results when using agents. As we show in our paper, a baseline agent without a well-tuned ACI does much worse than SWE-agent.
SWE-agent contains features that we discovered to be immensly helpful during the agent-computer interface design process:
- We add a linter that runs when an edit command is issued, and do not let the edit command go through if the code isn't syntactically correct.
- We supply the agent with a special-built file viewer, instead of having it just cat files. We found that this file viewer works best when displaying just 100 lines in each turn. The file editor that we built has commands for scrolling up and down and for performing a search within the file.
- We supply the agent with a special-built full-directory string searching command. We found that it was important for this tool to succintly list the matches- we simply list each file that had at least one match. Showing the model more context about each match proved to be too confusing for the model.
- When commands have an empty output we return a message saying "Your command ran successfully and did not produce any output."
@misc{yang2024sweagent,<br> title={SWE-agent: Agent Computer Interfaces Enable Software Engineering Language Models}, <br> author={John Yang and Carlos E. Jimenez and Alexander Wettig and Shunyu Yao and Karthik Narasimhan and Ofir Press},<br> year={2024},<br>}<br>
1/4
SWE-Agent is an open-source software engineering agent with a 12.3% resolve rate on SWE-Bench!
Check out SWE-agent in action at SWE-Agent
Repo: GitHub - princeton-nlp/SWE-agent: SWE-agent: Agent Computer Interfaces Enable Software Engineering Language Models
2/4
The SWE-agent open-source repository provides a framework for turning general LMs into software engineering agents. SWE-agent lets LMs like GPT-4 interact with their own Docker container using an Agent Computer Interface (ACI) - allowing it to browse, search, edit, and run code.
3/4
It’s been amazing to work on this with such a great team:
@jyangballin
*,[/URL]
@_carlosejimenez
*,[/URL]
@_awettig
,[/URL]
@ShunyuYao12
,[/URL]
@karthik_r_n
,[/URL] and
@OfirPress
Keep[/URL] an eye out for the paper coming out April 10th!
4/4
SWE-agent is our new system for autonomously solving issues in GitHub repos. It gets similar accuracy to Devin on SWE-bench, takes 93 seconds on avg + it's open source!
We designed a new agent-computer interface to make it easy for GPT-4 to edit+run code
GitHub - princeton-nlp/SWE-agent: SWE-agent: Agent Computer Interfaces Enable Software Engineering Language Models
SWE-Agent is an open-source software engineering agent with a 12.3% resolve rate on SWE-Bench!
Check out SWE-agent in action at SWE-Agent
Repo: GitHub - princeton-nlp/SWE-agent: SWE-agent: Agent Computer Interfaces Enable Software Engineering Language Models
2/4
The SWE-agent open-source repository provides a framework for turning general LMs into software engineering agents. SWE-agent lets LMs like GPT-4 interact with their own Docker container using an Agent Computer Interface (ACI) - allowing it to browse, search, edit, and run code.
3/4
It’s been amazing to work on this with such a great team:
@jyangballin
*,[/URL]
@_carlosejimenez
*,[/URL]
@_awettig
,[/URL]
@ShunyuYao12
,[/URL]
@karthik_r_n
,[/URL] and
@OfirPress
Keep[/URL] an eye out for the paper coming out April 10th!
4/4
SWE-agent is our new system for autonomously solving issues in GitHub repos. It gets similar accuracy to Devin on SWE-bench, takes 93 seconds on avg + it's open source!
We designed a new agent-computer interface to make it easy for GPT-4 to edit+run code
GitHub - princeton-nlp/SWE-agent: SWE-agent: Agent Computer Interfaces Enable Software Engineering Language Models
1/8
SWE-agent is our new system for autonomously solving issues in GitHub repos. It gets similar accuracy to Devin on SWE-bench, takes 93 seconds on avg + it's open source!
We designed a new agent-computer interface to make it easy for GPT-4 to edit+run code
github.com
2/8
SWE-agent works by interacting with a specialized terminal, which allows it to:
Open, scroll and search through files
Edit specific lines w/ automatic syntax check
Write and execute tests
This custom-built interface is critical for good performance!
2/N
3/8
Simply connecting an LM to a vanilla bash terminal does not work well.
Our key insight is that LMs require carefully designed agent-computer interfaces (similar to how humans like good UI design)
E.g. When the LM messes up indentation, our editor prevents it and gives feedback
4/8
Another example is that we discovered that for viewing files, letting SWE-agent only view 100 lines at a time was better than letting it view 200 or 300 lines and much better than letting it view the entire file.
Good agent-computer design is important even when using GPT-4.
4/N
5/8
SWE-agent can be easily configured and extended to improve future research on software engineering agents. Since SWE-agent is open source, anyone can experiment with and contribute new ways for agents to interact with computers.
5/N
6/8
Check out some cool demonstrations of SWE-agent fixing real GitHub issues at SWE-Agent!
6/N[/URL]
7/8
SWE-agent is a Princeton NLP collaboration by
@jyangballin
*,[/URL]
@_carlosejimenez
*,[/URL]
@_awettig
,[/URL]
@ShunyuYao12
,[/URL]
@karthik_r_n
,[/URL] and
@OfirPress
We’d[/URL] love to hear your thoughts, comments and questions! Here or on our discord at Join the SWE-agent Discord Server!
7/7[/URL]
8/8
Preprint coming next week!
SWE-agent is our new system for autonomously solving issues in GitHub repos. It gets similar accuracy to Devin on SWE-bench, takes 93 seconds on avg + it's open source!
We designed a new agent-computer interface to make it easy for GPT-4 to edit+run code
GitHub - princeton-nlp/SWE-agent: SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]
SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2...
github.com
2/8
SWE-agent works by interacting with a specialized terminal, which allows it to:
Open, scroll and search through files
Edit specific lines w/ automatic syntax check
Write and execute tests
This custom-built interface is critical for good performance!
2/N
3/8
Simply connecting an LM to a vanilla bash terminal does not work well.
Our key insight is that LMs require carefully designed agent-computer interfaces (similar to how humans like good UI design)
E.g. When the LM messes up indentation, our editor prevents it and gives feedback
4/8
Another example is that we discovered that for viewing files, letting SWE-agent only view 100 lines at a time was better than letting it view 200 or 300 lines and much better than letting it view the entire file.
Good agent-computer design is important even when using GPT-4.
4/N
5/8
SWE-agent can be easily configured and extended to improve future research on software engineering agents. Since SWE-agent is open source, anyone can experiment with and contribute new ways for agents to interact with computers.
5/N
6/8
Check out some cool demonstrations of SWE-agent fixing real GitHub issues at SWE-Agent!
6/N[/URL]
7/8
SWE-agent is a Princeton NLP collaboration by
@jyangballin
*,[/URL]
@_carlosejimenez
*,[/URL]
@_awettig
,[/URL]
@ShunyuYao12
,[/URL]
@karthik_r_n
,[/URL] and
@OfirPress
We’d[/URL] love to hear your thoughts, comments and questions! Here or on our discord at Join the SWE-agent Discord Server!
7/7[/URL]
8/8
Preprint coming next week!
http://github.com/princeton-nlp/SWE-agent…
SWE-Agent
@jyangballin
@_carlosejimenez
@_awettig
@ShunyuYao12
@karthik_r_n
@OfirPress
Join the SWE-agent Discord Server!
@yoheinakajima
@ChatGPTapp
discord.com
Join the SWE-agent Discord Server!
Check out the SWE-agent community on Discord - hang out with 4 other members and enjoy free voice and text chat.
SWE-Agent
@jyangballin
@_carlosejimenez
@_awettig
@ShunyuYao12
@karthik_r_n
@OfirPress
Join the SWE-agent Discord Server!
@yoheinakajima
@ChatGPTapp
discord.com
Join the SWE-agent Discord Server!
Check out the SWE-agent community on Discord - hang out with 4 other members and enjoy free voice and text chat.
xXMASHERXx
Superstar
What's funny is that every time this topic comes up, it's full of people who either don't work in the fields mentioned or have no idea what they are talking about 
these tools will be amazing for startups and organizations with small overheard/infrastructure
the code is barely optimized, have you heard of bitnet or 1bit models? these large language models will get much cheaper to run in a few years. the tech has a long way to go but a lot of people are working on making large language models cheaper to run.
Roger king
Superstar
This is pure cap there will always been need for hands on work and human experience especially for engineering
I ask "AI" to fix bugs for code it provides me on almost a daily basis, they'd program testing and automatically feeding errors back to it.
Welp…
Thank you for this reply as I must have been the only smooth brain to think the same thing
6 cert big dikk IT breh: "NooOooO"
Devin the AI- "OooOooO yeahhhhHhH"
i feel for the IT brehs as I wanted to be in the industry but God was like 
"nah chief, you got to sit this one out"
Most companies are barely even databases correctly, let alone on cloud.What's funny is that every time this topic comes up, it's full of people who either don't work in the fields mentioned or have no idea what they are talking about
Matter of fact excel is still the primary database for a lot companies.
The hire ups in a lot companies actually prefer to
Manipulate the data and read reports from excel.
If you know you know. @breakfuss
There’s also an energy capacity of limit to ai.
As Use of A.I. Soars, So Does the Energy and Water It Requires
Generative artificial intelligence uses massive amounts of energy for computation and data storage and millions of gallons of water to cool the equipment at data centers. Now, legislators and regulators — in the U.S. and the EU — are starting to demand accountability.
e360.yale.edu
More like recursive for Software Engineers. Someone has to develop the AI software that will be developing software
AI will do that since it's doing some of that already today. a lot of models are being trained on synthetic data(data generated by AI).
FishNGrits
Superstar
Nah if countries who use AI are out competing those who don’t you will just get left behind. Everyone will adopt it eventuallyThey won't let that fly in Europe or anywhere else..reducing 90% of your workforce to replace them with AI will only go in the US, nowhere else.
A dollar no matter the cost