@SwivalAgent
Account based inFrance
About this account
- Account based in
- France
- Connected via
- France App Store
Account-level information from X, not a live location or the device used for a specific post.
An AI coding agent for any model.
France
Joined May 2026
- Tweets262
- Following13
- Followers122
- Likes24
Swival.dev retweeted
Before you meet MiMo-V2.6, step into its world.
Every 3D model, game, slides, video, music and image in MiMo Gallery was generated by MiMo-V2.6.
Stay for the piano. Play a game. Catch the fireworks.
A first look at what's coming: mimo.xiaomi.com/mimo-gallery…
Toward Recursive Self-Improvement: How GLM Built Its Own Inference Infrastructure z.ai/blog/glm-built-its-infe…
Swival.dev retweeted
Hi Astra users. A reset and a quick update on quality issues that have been posted around.
Working with some of you, we have found and fixed the following issues:
- Some skills written for previous models were triggering too often or preventing the model from checking its work.
- An opt-in context management experiment that could cause early stops or replies to older messages. We've disabled it. Our rough estimate is that 4-5k users were affected by this experiment.
- We've also removed some badly configured engines that resulted in a measured quality degradation for a long tail of traffic flowing through them.
We’ve also made some more minor improvements and things should feel significantly better across the board. More consistent follow-through, better tracking of your latest message, and better checks on the work as it’s going through the motions.
The examples posted and all the users who worked directly with us were incredibly useful in helping fix things quickly. Always grateful for this incredible community.
And of course, a reset is also landing by midnight today.
Swival 1.0.44 released! It has quite a lot of internal changes. github.com/Swival/swival/rel…
Swival.dev retweeted
A year ago the question was which model. Now it's which harness.
Pi, Exo, Claude Code, Codex, DeepSeek Harness and 4 others. Same model, same tasks, same runtime. 360 runs, 2 billion tokens.
Pass rates: 50% to 67%.
Cost per pass: $1.05 to $18.34.
Introducing FrontierHarness Eval. 🧵
An academic survey on developer trust in AI-generated dependencies . Please fill it out, even if only for educational purposes.
vuamsterdam.eu.qualtrics.com…
Semaprax: The systems language built for coding agents, and readable by humans wavect.io/semaprax/
Swival.dev retweeted
We can finally talk about it:
We found a way to extract hidden reasoning of frontier models using a vulnerability in the APIs of every frontier AI company.
We verified that our reasoning token count matches billed API thinking tokens 1:1 for most of the prompts we queried.
Introducing NVIDIA Nemotron 3.5 Lightning⚡
An open 30B MoE model with 3B active parameters, built for always-on agents to complete high-volume, specialized tasks faster.
It delivers up to 4x the output speed of similar-sized models.
That was quick: claudewatermarkremover.app
Anthropic just added watermarks to all Claude generated content: support.claude.com/en/articl…
