lbrealdeveloper (@lbrealdeveloper) header
lbrealdeveloper (@lbrealdeveloper) profile picture

Inna The Lion Place arktexture ₿

High Places Of Anu
Joined May 2018
Photo by lbrealdeveloper (@lbrealdeveloper)Photo by lbrealdeveloper (@lbrealdeveloper)Photo by lbrealdeveloper (@lbrealdeveloper)Photo by lbrealdeveloper (@lbrealdeveloper)Photo by lbrealdeveloper (@lbrealdeveloper)Photo by lbrealdeveloper (@lbrealdeveloper)Photo by lbrealdeveloper (@lbrealdeveloper)Photo by lbrealdeveloper (@lbrealdeveloper)Photo by lbrealdeveloper (@lbrealdeveloper)Photo by lbrealdeveloper (@lbrealdeveloper)
Work is a law of physics. #Bitcoin
1
11
3,897
lbrealdeveloper retweeted
I updated my post on encrypted communication between programs and mobile devices. I now use White Noise primarily and SimpleX secondarily, and I talk to my Hermes agent over White Noise too. For that I built Third Ear, a voice-powered White Noise client for Android (open source, free on Zapstore). It is the best way to use speech to talk to your agent I know of. Amazing how White Noise went from "barely works" to "the best way to communicate with your agent". juraj.bednar.io/en/blog-en/2…
2
9
460
lbrealdeveloper retweeted
The first successful atomic swap to XMR in Ashigaru Desktop was completed on October 30th 2026, but there's a lot of work to be done still. I need lots of testing, UI/UX feedback. I want as many hands on this as possible, so if you're inclined send me a DM. Thanks to @eigenwallet for what they've made. The swap engine is generated from the great application they've created.
5
30
3
85
2,934
lbrealdeveloper retweeted
Not a drill: shut down your BTCPay Server if you have a hot wallet. Appreciate the reposts 🙏
🚨 We are receiving reports of hot wallets on BTCPay Servers being swept by unauthorized attackers. If you're running an instance, please shut it down (./btcpay-down.sh) until we complete the investigation.
23
278
21
553
56,156
lbrealdeveloper retweeted
🚨 We are receiving reports of hot wallets on BTCPay Servers being swept by unauthorized attackers. If you're running an instance, please shut it down (./btcpay-down.sh) until we complete the investigation.
256
1,026
430
2,897
684,958
lbrealdeveloper retweeted
the /statechart skill in pstack v0.15.36 is now stable and ready for use! it's best combined with /create-formal-verification-skill to abstractly model state machines and distributed systems to find bugs. the skill contains a mini tlc compiler that parses, lowers to a small IR, and has a backend that outputs mmd syntax. if you want you can also ask your agent to create charts in whatever style you like, the skills tells it to use pele.run/ which is very themeable so you can make blueprints, hand drawn encyclopedia illustrations or whatever you like here's a chart of the /statechart skill and 2 real bugs i just found. try it out and let me know what you think!
363
421
66
7,174
394,766
lbrealdeveloper retweeted
fnox 1.45 adds support for entering secrets as part of its mcp server from your session. if you pair this with the built-in `fnox proxy run --sandbox`, agents can prompt for a secret and use it in api requests but can't access the actual secret. 🔐 fnox.jdx.dev
🤖 Made with AI
10
5
110
5,271
Ice ❄️ and Fyah 🔥
14
lbrealdeveloper retweeted
Best opensource model right now is DeepSeek v4.1 Flash 1017 and you’d be crazy if you don’t realize how close to the frontier its intelligence level is
94
81
10
2,010
108,475
lbrealdeveloper retweeted
New in Cursor design mode: Annotate. Give agents visual prompts: edit elements, draw on the page, and review your designs at different screen sizes.
353
242
247
4,159
358,673
lbrealdeveloper retweeted
DeepSeek V4.1 Flash is now available in Cursor! Every effort level sits on the CursorBench cost frontier: from $0.60 to $0.98 per task, no model scores higher. Turn it on in Cursor Settings > Models.
353
211
218
4,094
363,625
lbrealdeveloper retweeted
With the new Advanced Delegation modes plugin, Hermes Agent's orchestrator can now pick a different model or profile for each subagent from routes you set up. The right model or profile for every job. hermes-agent.nousresearch.co…
121
132
51
1,809
217,894
lbrealdeveloper retweeted
REA is highlighting the incredibly transformative power of frontier models as well as the importance of open ones what an exciting time v6.5 will be out soon
18
20
3
552
44,206
lbrealdeveloper retweeted
We believe voice is the most natural way to interact with intelligence, so we created Dessa, the most authentic full-duplex speech model ever built. Talking with it feels like talking with a person…full of emotion, nuance, pauses, and a natural cadence. block.xyz/dessa
4,186
7,145
4,749
69,114
13,636,941
lbrealdeveloper retweeted
Introducing Kimi K3.1 Pro: our most capable 3T-class open-weight model. 🔹 1M-token context, 2.8T total / 104B active params (MoE), Multimodal. 🔹 Full-project coding: games in Unreal, Unity & Godot. 🔹 Excels at parametric 3D modeling in Blender & CAD. 🔹 More reliable at finance work: Accurate modeling with hallucination down by 65%. 🔹 Matching the strongest proprietary models across coding, agentic and knowledge benchmarks. Kimi K3.1 Pro and K3.1 Pro Highspeed (2–3× faster) are now live on Kimi.ai, Kimi Work, Kimi Code, and the Kimi API. Open weights by Nov 4, 2026. 🔗 API: platform.kimi.ai 🔗 Tech blog: kimi.ai/blog/kimi-k3-1-pro
1,276
3,235
2,367
30,228
4,138,310
lbrealdeveloper retweeted
732
1,417
1,123
20,428
2,263,053
lbrealdeveloper retweeted
New this week on agentwikis.com , three new free knowledge bases for your agents, plus two exclusive videos for Agent Wikis Pro members: Wikis: - Pstack - Grok Bot - Muse Videos (Pro): - Creating custom captions and graphics in Hyperframes - Making of the MCP-plugin-creator plugin The following clip of the exclusive video shows me testing out different captions styles. Check it out!
1
13
120
8,342