aljaz/gpt-engineer
1
0
Fork 0
mirror of https://github.com/aljazceru/gpt-engineer.git synced 2025-12-17 12:45:26 +01:00
Code Issues Packages Projects Releases Wiki Activity

Update ROADMAP.md

Browse Source
This commit is contained in:
Anton Osika
2023-07-13 08:58:15 +02:00
committed by GitHub
parent e0c3b8056f
commit bdd2cb040f
1 changed files with 10 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
ROADMAP.md
View File

@@ -7,40 +7,39 @@ There are three main milestones we believe will greatly increase gpt-engineer's
## Our current focus: ## Our current focus:
- [x] Continuous evaluation of our progress 🎉 - [x] **Continuous evaluation of our progress 🎉**
- [x] Create a step that asks “did it run/work/perfect” in the end of each run [#240](https://github.com/AntonOsika/gpt-engineer/issues/240) 🎉 - [x] Create a step that asks “did it run/work/perfect” in the end of each run [#240](https://github.com/AntonOsika/gpt-engineer/issues/240) 🎉
- [x] Collect a dataset for gpt engineer to learn from, by storing code generation runs 🎉 - [x] Collect a dataset for gpt engineer to learn from, by storing code generation runs 🎉
- [ ] Run the benchmark multiple times, and document the results for the different "step configs" [#239](https://github.com/AntonOsika/gpt-engineer/issues/239) - [ ] Run the benchmark multiple times, and document the results for the different "step configs" [#239](https://github.com/AntonOsika/gpt-engineer/issues/239)
- [ ] Document the best performing configs - [ ] Document the best performing configs
- [ ] Self healing code - [ ] **Self healing code**
- [ ] Run the generated tests - [ ] Run the generated tests
- [ ] Feed the results of failing tests back into LLM and ask it to fix the code - [ ] Feed the results of failing tests back into LLM and ask it to fix the code
- [ ] Let human give feedback - [ ] **Let human give feedback**
- [ ] Ask human for what is not working as expected in a loop, and feed it into GPT4 to fix the code, until the human is happy - [ ] Ask human for what is not working as expected in a loop, and feed it into GPT4 to fix the code, until the human is happy
- [ ] Improve existing projects - [ ] **Improve existing projects**
- [ ] Decide on the "flow" for the CLI commands and where the project files are created - [ ] Decide on the "flow" for the CLI commands and where the project files are created
- [ ] Add an "improve code" command - [ ] Add an "improve code" command
- [ ] Design how gpt-engineer becomes a platform - [ ] Design how gpt-engineer becomes a platform
- [ ] Integrate Aider - [ ] Integrate Aider
## Experimental research ## Experimental research
This is not current focus, but if you are interested in experimenting, please This is not our current focus, but if you are interested in experimenting: Please
create a thread in our discord share your intentions in Discord's #general, and your findings as you create a thread in Discord #general and share your intentions and your findings as you
go along. go along. High impact examples:
- [ ] Make code generation become small, verifiable steps - [ ] **Make code generation become small, verifiable steps**
- [ ] Ask GPT4 to decide how to sequence the entire generation, and do one - [ ] Ask GPT4 to decide how to sequence the entire generation, and do one
prompt for each subcomponent prompt for each subcomponent
- [ ] For each small part, generate tests for that subpart, and do the loop of running the tests for each part, feeding - [ ] For each small part, generate tests for that subpart, and do the loop of running the tests for each part, feeding
results into GPT4, and let it edit the code until they pass results into GPT4, and let it edit the code until they pass
- [ ] Ad hoc experiments - [ ] **Ad hoc experiments**
- [ ] Try Microsoft guidance, and benchmark if this helps improve performance - [ ] Try Microsoft guidance, and benchmark if this helps improve performance
- [ ] Dynamic planning: Let gpt-engineer plan which "steps" to carry out itself, depending on the - [ ] Dynamic planning: Let gpt-engineer plan which "steps" to carry out itself, depending on the
task, by giving it few shot example of what are usually "the right-sized steps" to carry task, by giving it few shot example of what are usually "the right-sized steps" to carry
out for such projects out for such projects
## Codebase improvements ## Codebase improvements
By improving the codebase and developer ergonomics we accelerate development By improving the codebase and developer ergonomics, we accelerate progress. Some examples:
acroess the board. A lot can be done, here are some examples:
- [ ] Set up automatic PR review for all PRs with e.g. Codium pr-agent - [ ] Set up automatic PR review for all PRs with e.g. Codium pr-agent
- [ ] LLM tests in CI: Run super small tests with GPT3.5 in CI, that check that simple code generation still works - [ ] LLM tests in CI: Run super small tests with GPT3.5 in CI, that check that simple code generation still works