xoots (@xoots1) header
xoots (@xoots1) profile picture

alpha xoots

Joined February 2019
Photo by xoots (@xoots1)Photo by xoots (@xoots1)Photo by xoots (@xoots1)Photo by xoots (@xoots1)Photo by xoots (@xoots1)Photo by xoots (@xoots1)Photo by xoots (@xoots1)Photo by xoots (@xoots1)Photo by xoots (@xoots1)Photo by xoots (@xoots1)
xoots retweeted
chat wtf is my intern talking about
23
58
4
4,339
316,479
xoots retweeted
Idle tokens are a bug. Today that changes. Hive connects you to Interest from the internet. Your stablecoins, earning across multiple lending markets. Non-custodial. Withdraw anytime. Hive is live on Solana. Go try it ⬇️🐝
32
17
2
132
28,580
xoots retweeted
Sometimes I ask myself if this is true
7,810
9,024
2,657
88,026
97,685,357
xoots retweeted
new walk of shame: agent still working, but the cafe closed
256
183
105
5,376
607,024
haven’t tried it fully but it’s better and cheaper than 3.2, so massive
Matthew is locked in. I 100% agree just cause the coders aren’t impressed doesn’t mean that this isn’t going to change the economics of AI in corporations
69
cool to see @NousResearch integrate with open source hard. been running evolution loops for a few weeks with m2.7 in the hermes harness, tool calling improvements are coming along nicely
Capable agents are the result of co-evolution between models and harnesses. We've been working with @NousResearch to ensure that M2.7 x Hermes Agent provides a top-tier experience for users. Hermes’s self-improving loop brings out the best in M2.7 through real usage. We are also launching MaxHermes, a cloud-hosted and managed version of Hermes in @MiniMaxAgent (No terminal setup, no config) If you’re already running Hermes locally, you can now give you agent a partner in the cloud with MaxHermes. The path to AGI is shorter with good company. @NousResearch 🤝 @MiniMax_AI
63
if you're not running Gemma 4 E4B on locally on your airpods you're falling behind
95
165
24
3,009
146,638
I ran 110 million tokens through the DeepSeek API in March. Autonomous agents. Research pipelines. Overnight coding sprints. 7,030 API calls. My bill was $6.84. Here’s how it worked, what breaks it, and how to set it up so you can do the same thing. 🧵
🤖 Made with AI
3
1
1
5
589
Claude caching is different. Anthropic uses explicit cache breakpoints in the API, shorter TTL windows, and different tradeoffs. We’re hitting ~88% there too, but you earn it differently. If you want that breakdown next, I’ll post it. Same outcome, different method.
1
2
39
Drop a comment if this was helpful and you plan to try this setup. I’ll drop a guide on using deepseek for coding specific tasks and harness findings that improved quality output and spammed less api calls to do the same tasks. Stay tuned🐋
2
39