Give your AI coding agents the codebase knowledge your team spent years building.
Joined September 2025
- Tweets 40
- Following 42
- Followers 8
- Likes 1
5 Photos and videos
Apr 6
We ran the same eval on OpenAI Codex.
Same benchmarks, same methodology as the Claude eval. Results hold.
🧵
1
1
11
Apr 6
Works with Claude Code. Works with OpenAI Codex. Works with all major coding agents.
$5 per repo, one-time.
Code CODESETLAUNCH for a free trial → codeset.ai
1
9
Mar 19
We made Haiku as good as Opus. Without changing the model.
Today we're launching Codeset. Here's what we found 🧵
2
3
6
511
Mar 19
Results? On our benchmarks, Haiku Codeset performs better than vanilla Opus at nearly 1/10th the cost!
The next leap in AI coding won't come from smarter models alone. It'll come from models that finally know where they are.
1
1
2
78
15 Oct 2025
What's next: more languages, additional task types beyond issue resolution, support for other public datasets, and custom datasets on commission.
We're building this for teams working on the next generation of code agents.
1
48
15 Oct 2025
Try it now:
🔗 Platform: codeset.ai
📚 Docs: docs.codeset.ai
💾 Dataset: huggingface.co/datasets/code…
$5 free credits, pay-as-you-go, no minimum commitment. We'd love your feedback as we build this out.
1
44
2 Oct 2025
🔎 Paper 2 in the Codeset Paper Series:
CWM - An Open-Weights LLM for Research on Code Generation with World Models
by @TacoCohen @adiyossLC @syhw and the Meta FAIR CodeGen Team
1
1
94
2 Oct 2025
We believe that the future of code LLMs lies in understanding computational environments. For this, we need to scale executable data and improve both state observability and verification. Our platform will enable anyone to easily train models that reason about code execution.
1
31
2 Oct 2025
Read more about CWM at ai.meta.com/research/publica…
Read more about Codeset at codeset.ai/
29