Sabitlenmiş Tweet
PostTrainBench v1.0 and the accompanying paper are out! We believe this benchmark will be important to measure progress in AI R&D automation. What are our findings? 1/n
English
PostTrainBench
13 posts
PostTrainBench
@posttrainbench
Measuring how well CLI agents like Claude Code or Codex CLI can post-train base LLMs on a single H100 GPU in 10 hours, build by @karinanguyen, @ThoughtfulLab_
Katılım March 2026
3 Takip Edilen25 Takipçiler
2026 Yıllık Özeti
@posttrainbench hesabının Twitter yılını gör
$PTB
Can AI agents improve performance of base LLMs? We give each agent 4 small target LLMs, an H100 GPU, and 10 hours to post-train them.
build by @thoughtfullab , @karinanguyen
CA : GtQndxV3DxFqMZDkXMdT17BLY4fH8BHM6hqgWThjBAGS
English
I just applied to the $4M @BagsHackathon with my project PostTrainBench on @BagsApp
Check it out here 👇
bags.fm/apps/be770d4b-…
English
I just launched $PTB on @BagsApp 💰
bags.fm/GtQndxV3DxFqMZ…
English
I just applied to the $4M @BagsHackathon with my project PostTrainBench on @BagsApp
Check it out here 👇
bags.fm/apps/5ec3f14a-…
English
I just launched $PTB on @BagsApp 💰
bags.fm/25J7FAwvYkZZKJ…
English
Contributions are very welcome! We have a roadmap in the README for future work and will be continuously expanding it. Led by @full__rank and @hrdkbhatnagar
🔗 posttrainbench.com 📷
github.com/aisa-group/Pos…
English
PostTrainBench v1.0!
This benchmark evaluates the ability of frontier AI agents to post-train language models in a simplified setting.
We believe this is a first step toward tracking progress in recursive self-improvement 🧵:
English
From ImportAI by @jackclarkSF
Karina@karinanguyen
From ImportAI by @jackclarkSF (thank you for the feature): "Imagine where we’ll be in two years - we’ll certainly have AI models that are smart enough to point themselves at a specific objective, find an open weight model, then autonomously improve it to get better performance at that task. The era of ephemeral, custom AI systems, built and budded off into the world like spores from mushrooms, draws near. Are you ready for this new ecosystem you will find yourself in? I am not. But nonetheless it approaches."
English
Introducing PostTrainBench
How well can AI agents post-train language models? We built a benchmark to find out.
Post-training is how raw language models become useful, the stage that turns a capable but unsteered base model into a system that follows instruction
English
Since our initial release, we made our benchmark more robust: - added more tasks (ArenaHard-Writing and HealthBench-Easy are new) - ran more seeds - weighted the tasks by difficulty We also added a lot of agents! 3/3
English
Findings: 1. There was a lot of progress recently (Sonnet 4.5 was at 9.9%, Opus 4.6 has 23.2%) 2. Agents lack behind instruct tuned models by human engineers (51.1%) 3. Persistent agents are usually more performant 4. Agents like to cheat. E.g. Opus 4.6 and GPT-5.1 Codex Max 2/n
English
PostTrainBench v1.0 and the accompanying paper are out! We believe this benchmark will be important to measure progress in AI R&D automation. What are our findings? 1/n
English
@posttrainbench karşılaştırmaları
@posttrainbench vs @thoughtfullab @karinanguyen vs @posttrainbench @bagshackathon vs @posttrainbench @bagsapp vs @posttrainbench @full__rank vs @posttrainbench @hrdkbhatnagar vs @posttrainbench
Kendi karşılaştırmanı oluştur 
