| 1. | | Show HN: RULER – Easily apply RL to any agent (openpipe.ai) |
| 81 points by kcorbitt 89 days ago | past | 11 comments |
|
| 2. | | Everything I know about reward hacking (openpipe.ai) |
| 3 points by kcorbitt 3 months ago | past |
|
| 3. | | Show HN: ART – a new open-source RL framework for training agents (github.com/openpipe) |
| 116 points by kcorbitt 5 months ago | past | 12 comments |
|
| 4. | | ART·E: how we built an email research agent that beats o3 (openpipe.ai) |
| 3 points by kcorbitt 5 months ago | past | 2 comments |
|
| 5. | | Using GRPO to Beat o1, o3-mini and R1 at “Temporal Clue” (openpipe.ai) |
| 199 points by kcorbitt 7 months ago | past | 55 comments |
|
| 6. | | Analyzing OpenAI's Reinforcement Fine-Tuning: Less Data, Better Results (openpipe.ai) |
| 4 points by kcorbitt 9 months ago | past |
|
| 7. | | Using reinforcement learning and $4.80 of GPU time to find the best HN post (openpipe.ai) |
| 217 points by kcorbitt 11 months ago | past | 95 comments |
|
| 8. | | Show HN: Agent.exe, a cross-platform app to let 3.5 Sonnet control your machine (github.com/corbt) |
| 406 points by kcorbitt 11 months ago | past | 232 comments |
|
| 9. | | DPO fine-tuning outperforms SFT (openpipe.ai) |
| 1 point by kcorbitt on Oct 2, 2024 | past |
|
| 10. | | OpenPipe Mixture of Agents: Outperform GPT-4 at 1/25th the Cost (openpipe.ai) |
| 13 points by kcorbitt on June 20, 2024 | past | 2 comments |
|
| 11. | | What we've learned in 3 days of Llama 3 (openpipe.ai) |
| 3 points by kcorbitt on April 22, 2024 | past |
|
| 12. | | Mixtral Curious? Comparing Mistral 7B and Mixtral for fine-tuning (openpipe.ai) |
| 1 point by kcorbitt on Feb 29, 2024 | past |
|
| 13. | | S-LoRA: Serving Thousands of Models from One GPU for Fun and Profit (openpipe.ai) |
| 1 point by kcorbitt on Jan 18, 2024 | past |
|
| 14. | | Is AI the next crypto? Insights from HN comments (openpipe.ai) |
| 237 points by kcorbitt on Nov 8, 2023 | past | 367 comments |
|
| 15. | | Fine-tune your own Llama 2 to replace GPT-3.5/4 |
| 955 points by kcorbitt on Sept 12, 2023 | past | 181 comments |
|
| 16. | | Show HN: Automatically convert your GPT-3.5 prompt to Llama 2 |
| 13 points by kcorbitt on Aug 9, 2023 | past | 2 comments |
|
| 17. | | TaxyAI: Open-source browser automation with GPT-4 (github.com/taxyai) |
| 355 points by kcorbitt on March 28, 2023 | past | 99 comments |
|
| 18. | | Tell HN: YC will help you find a co-founder |
| 433 points by kcorbitt on July 6, 2021 | past | 131 comments |
|
| 19. | | YC Startup School for future founders who aren't quite ready to start yet (blog.ycombinator.com) |
| 330 points by kcorbitt on Oct 30, 2020 | past | 87 comments |
|
| 20. | | YC's Startup School Relaunching as Continuous Program (blog.ycombinator.com) |
| 330 points by kcorbitt on June 17, 2020 | past | 58 comments |
|
| 21. | | As Uber and Tesla struggle with driverless cars, Waymo moves forward (arstechnica.com) |
| 76 points by kcorbitt on June 1, 2018 | past | 48 comments |
|
| 22. | | McKinsey: One-third of US workers could be jobless by 2030 due to automation (cnbc.com) |
| 5 points by kcorbitt on Nov 29, 2017 | past | 1 comment |
|
| 23. | | Startup Ideas (blog.ycombinator.com) |
| 614 points by kcorbitt on Nov 16, 2017 | past | 453 comments |
|
| 24. | | Sam Altman presents a political vision for California and the U.S (techcrunch.com) |
| 1 point by kcorbitt on July 13, 2017 | past |
|
| 25. | | A ReasonReact Tutorial (jaredforsyth.com) |
| 161 points by kcorbitt on July 6, 2017 | past | 28 comments |
|
| 26. | | US Household Debt Surpasses 2008 High (nytimes.com) |
| 250 points by kcorbitt on May 17, 2017 | past | 418 comments |
|
| 27. | | New attack that cripples HTTPS crypto works on Macs, Windows, and Linux (arstechnica.com) |
| 250 points by kcorbitt on July 26, 2016 | past | 68 comments |
|
| 28. | | Evernote limits free tier to two devices, raises prices 40% (arstechnica.com) |
| 13 points by kcorbitt on June 29, 2016 | past | 1 comment |
|
| 29. | | Report: Apple is approving apps more quickly to increase Services revenue (arstechnica.com) |
| 1 point by kcorbitt on May 12, 2016 | past |
|
| 30. | | One Day with React Native for Android (corbt.com) |
| 2 points by kcorbitt on Sept 16, 2015 | past |
|
|
| More |
