posts
- Secure session ready. Battery: ?
Porting an encrypted BLE handshake from Python to an ESP32-S3: every step reported success, and the reads came back empty. The station sends its key twice.
- The power went out twice. My UPS log saw it once.
Monitoring a BLUETTI AC180 used as a home UPS from Linux over encrypted BLE: no account needed, but polling misses short outages and input watts lie.
- The fastest model finished first by stopping first
gpt-oss-120b cleared six agent cells in 51 minutes by quitting early on each. Two of those stops shipped Zig that does not compile.
- IOMMU off buys a 128 GB iGPU 5 %, and costs the NPU
On this Strix Halo box the GPU was never behind IOMMU translation, so iommu=pt changed nothing for it. amd_iommu=off bought ~5 % prefill and killed the NPU.
- Read the transcript, not the gate
15 of 17 local models passed the agent smoke gate on the 128 GB box. Eight of those passes hid a Claude Code failure the intake had logged and nobody read.
- The benchmark was talking to the previous server
A Flash-Next-only engine, three modes, and a mode result that was really the previous run's server: how cd && server & made $! lie.
- Mistral-Small-4 ran one matmul on the CPU, and said nothing
Mistral-Small-4 decoded at 3.4 tok/s with the model on the GPU: one op per layer ran on the CPU, silently. MiniMax was slow in a different way.
- Vulkan or ROCm on Strix Halo? Ask at which depth
On an empty context Vulkan won the first-day bench on every model. At 127k, ROCm prefilled gpt-oss-120b 7× faster. The answer depends on depth.
- The deadlock test can't see a half-held lock
Every model wrote a thread test. Most of them could not fail: with locks taken in id order, opposite-direction transfers serialize on one mutex.
- Zig's defer ends at the closing brace
A local model locked two accounts in the right order, scored 97/100, and lost money. One Zig defer sat inside an if block and unlocked at the brace.