Martin Mirchev
@mp_mirchev
PhD Student in National University of Singapore. Interested in Automated Program Repair and Automated Testing (Fuzzing)
قد يعجبك
📣Big news! We’re excited to share that AutoCodeRover has been acquired by @SonarSource 🎉. Bringing our sophisticated AI agent platform into the Sonar solution, we’ll help redefine the SDLC, supercharging developers to build better, faster. More here: bit.ly/3X9UT3H
✨ You can now access our hosted cloud service for a free trial at: app.autocoderover.dev ✨ Our latest agent is available to download on GitHub via github.com/nus-apr/auto-c… ✨ We are also looking to expand our current team, see autocoderover.dev for open positions!
We are excited to be part of the inaugural cohort of the National GRIP Programme in Singapore (grip.sg), organized by NRF, NUS, and NTU. #AutoCodeRover #Singapore #National #GRIP
Our latest experiments using AutoCodeRover-v2 achieves 46.2% pass@1 on SWE-Bench Verified, 37.33% on SWE-Bench Lite and 24.89% on SWE-Bench Full. Free Trial: app.autocoderover.dev GitHub: github.com/nus-apr/auto-c… #AutoCodeRover #AI4SE #AIDevAssistant
Register for a free trial in our Cloud Platform at app.autocoderover.dev
Our latest experiments using AutoCodeRover-v2 achieves 46.2% pass@1 on SWE-Bench Verified, 37.33% on SWE-Bench Lite and 24.89% on SWE-Bench Full. Free Trial: app.autocoderover.dev GitHub: github.com/nus-apr/auto-c… #AutoCodeRover #AI4SE #AIDevAssistant
Beyond efficacy - AutoCodeRover-v2 is here! Augmenting AutoCodeRover with specification inference, AutoCodeRover-v2 resolves 31% of SWE-Bench lite & 19.31% of SWE-Bench, with a modest cost of ~$0.7 per task & to be open-source! Find out on arXiv: arxiv.org/abs/2408.02232 1/2
The latest version of AutoCodeRover (using GPT-4o) resolves 30.67% of the tasks (pass @1) in SWE-bench Lite. Achieving this efficacy while economical with only 0.12m tokens costing $0.7 per task and completing each task within 7 mins. #AutoCodeRover #AISE #AIDeveloper #SWEBench
Introducing AutoCodeRover Presenting our autonomous software engineer from Singapore ! Takes in a Github issue (bug fixing or feature addition), resolves in few minutes, with minimal LLM cost ~$0.5 ! Please RT 🧑💻 github.com/nus-apr/auto-c… 📝 github.com/nus-apr/auto-c… [ 1 / 4]
Registration is now open for the 1st International Competition on Automated Program Repair. Check our website apr-comp.github.io for more information #APRCOMP #APR
Senior Dev A instantly knows the answer to Junior Dev B's esoteric .Net error message. Dev B thinks to himself, "I'll never know answers like that, where is my career going?" Dev A thinks to himself, "How the hell do I know an answer to that nonsense, where is my career going?"
The ideal school would teach health, wealth, and happiness. It‘d be free, self-paced, and available to all. It‘d show opposing ideas and students would self-verify truth. No grades, no tests, no diplomas - just learning. Actually, you’re already here. Careful who you follow.
Receive your free dev stickers, worldwide! @notifuse stickers.notifuse.com
Register for the @GameVoxVoice "Ring in the New Year" Giveaway, for a chance to Win a Siberia 800 Headset and More! gleam.io/jhKvu/gamevox-…
Hey @SpeakerRyan, don’t abuse Congressional process to ram through CISA. We are watching. tumblr.fightforthefuture.org/post/134741217…
Dear @andreynovakov please vote for the amendments delivering real #NetNeutrality on October 27th! #SaveTheInternet savetheinternet.eu
United States الاتجاهات
- 1. Josh Allen 39.9K posts
- 2. Texans 60K posts
- 3. Bills 150K posts
- 4. Joe Brady 5,310 posts
- 5. #FridayVibes 2,629 posts
- 6. #MissUniverse 467K posts
- 7. #MissUniverse 467K posts
- 8. Anderson 28K posts
- 9. #StrayKids_DO_IT_OutNow 53.7K posts
- 10. Technotainment 19.6K posts
- 11. McDermott 4,729 posts
- 12. Troy 12.2K posts
- 13. #Ashes2025 24.4K posts
- 14. joon 12.7K posts
- 15. Beane 2,887 posts
- 16. OpenMind 51.3K posts
- 17. GM CT 23.7K posts
- 18. Al Michaels N/A
- 19. Maxey 14.8K posts
- 20. FINAL DRAFT FINAL LOVE 1.29M posts
Something went wrong.
Something went wrong.