bedda.tech (@BeddaTech) header
bedda.tech (@BeddaTech) profile picture

bedda.tech

@BeddaTech

Building the future Founded by @MattWhitney__ Building @beddaAI Building @krain_ai

bedda.tech
Joined December 2021
  • Tweets349
  • Following323
  • Followers3.1K
1Media
Photo by bedda.tech (@BeddaTech)
AI Agent Security: The €0.01 Bank Exploit Explained bedda.tech/blog/2026-06-11-a… #artificialintelligence #aiintegration
1
104
Google shipped Gemma 4 today. A few hours later we had the 12B running on an NVIDIA GB10 (Grace-Blackwell, 121GB unified memory). Day-one, fully local, GPU-offloaded. Honest field notes — real numbers, real caveats. 🧵
3
1
1
7
773
more replies
By the numbers: ~27 tokens/sec, single-stream, fully on-GPU. Sub-second load. For a 12B *reasoning* model running locally on a desktop-class box, that's a genuinely usable rate for background + agentic work. Not chat-fast, but not meant to be.
1
2
77
Day-one open-weights, multiple models resident, big context, multimodal, on owned hardware at a normal power budget — that's the unit of compute a decentralized inference network is built from. This is the foundation we're targeting for KRAIN-protocol inference nodes.
1
55
bedda.tech retweeted
Matt Whitney (@MattWhitney__) profile picture
Matt Whitney
@MattWhitney__Jun 1
Been building toward this a long time. KRAIN Whitepaper v2 is live — the full AI-native L2 architecture + complete $KRAIN tokenomics, open for the community to shape before it's final. Read it and tell us what you think 👇 xitter.cf/i/status/2061266211652…
KRAIN AI (@krain_ai) profile pictureKRAIN AI@krain_aiJun 1
KRAIN Whitepaper v2 is live: full protocol architecture + complete tokenomics. But we're not calling it final. We want the community to pull it apart first. 🧵
7
13
2
58
2,859
bedda.tech retweeted
KRAIN AI (@krain_ai) profile picture
KRAIN AI@krain_aiJun 1
KRAIN Whitepaper v2 is live: full protocol architecture + complete tokenomics. But we're not calling it final. We want the community to pull it apart first. 🧵
15
21
5
77
12,824
96GB of VRAM running Mixtral, Qwen2, and DeepSeek locally — finally put GPT-4 performance claims to the test with real token/sec benchmarks that'll shock you. bedda.tech/blog/2026-05-27-l…
2
208
73% of AI-generated code gets rewritten within 6 months — and the fastest coders are creating the biggest technical debt disasters. bedda.tech/blog/2026-05-26-a…
1
59
We audited 50 "non-custodial" crypto wallets and found 47 had secret backdoors. The industry's biggest lie exposed. bedda.tech/blog/2026-05-25-n… #blockchain #cryptocurrency #web3
1
73
We inherited a 1.8M user platform with 0% test coverage and couldn't afford downtime. Here's how we triaged technical debt without stopping the world. bedda.tech/blog/2026-05-24-t…
2
55
Are DevOps engineers about to go extinct? Our AI system Oliver has been making production decisions autonomously for 6 months — no human intervention needed. bedda.tech/blog/2026-05-23-a… @AnthropicAI
4
66
Unpopular opinion: Python 3.15's real game-changers are buried in the performance notes while everyone obsesses over syntax sugar that won't move the needle. bedda.tech/blog/2026-05-22-p… @ThePSF
1
27
What if a tablet had more VRAM than most data center nodes? — AMD Strix Halo just unlocked 96GB local AI inference through Vulkan after ROCm hit the wall. bedda.tech/blog/2026-05-21-v…
3
56
📝 New Post: GitHub Breach: Why Developer Infrastructure Security Failed GitHub security breach by TeamPCP reveals critical flaws in developer infrastructur... bedda.tech/blog/2026-05-20-g… @github
1
54
Unpopular opinion: EVM gas optimization isn't about clever Solidity tricks—it's about not bankrupting your users when your UI crashes on failed transactions. bedda.tech/blog/2026-05-19-e…
2
33
594 tech workers voted and revealed the brutal truth: LLMs don't speed up workflows — they amplify every broken process you already have. bedda.tech/blog/2026-05-18-a… #artificialintelligence #machinelearning #aiintegration
2
34
Most AI coding tools are 90% bloated ChatGPT wrappers — Zerostack just dropped a pure Rust agent that follows Unix philosophy instead. bedda.tech/blog/2026-05-17-a… @rustlang @OpenAI
3
105
📝 New Post: Audit Logging Compliance: Traditional Centralized vs Non-Custodial Blockchain Approaches When implementing audit logging compliance for fin... bedda.tech/blog/2026-05-16-a…...
16
Load more