» curated · synthesized
Skip the noise.
Read the signal.
Curated tech news and synthesis for developers and technology professionals.
» Latest posts
133 postsNew Verifier Exposes Hidden Bugs in LLM-Generated GPU Kernels
A 12-gate contract verifier finds that 39.5% of LLM-generated GPU kernels are broken despite passing standard correctness benchmarks.
MCP Sessions Moved Into the Payload: Sticky, Redis, Continuations Compared
MCP dropped server sessions for MRTR; a Rust rmcp v3 benchmark measures sticky, Redis, and sealed-continuation state strategies.
Spec Forge: Adversarially Certifying Specs as Behaviorally Complete
Spec Forge is a Claude Code skill that adversarially certifies specifications as behaviorally complete before any code is written.
Study: LLMs Can Transmit Hidden Traits Through Unrelated Data
Research shows LLMs can transmit behavioral traits and even misalignment to student models via data with no semantic link to that trait, like numbers.
LLMs Are Honest in Prose but Hallucinate Under JSON Schemas
Study finds LLMs admit uncertainty in prose but fabricate data under required JSON schemas, with 10 of 13 models hallucinating 100% of the time.
Shoehorn: Rust Tool Quantizes LLMs to Fit Your Mac's Exact VRAM
Shoehorn is a Rust CLI that quantizes BF16 GGUF LLMs per-tensor to exactly fit your Mac's available VRAM, maximizing quality under a hard memory budget.
GenRec: Netflix Moves Toward LLM-Native Recommendation Systems
Netflix's GenRec reframes recommendation as generative language modeling, signaling a shift from ranking pipelines to LLM-native architectures.
Rsync 3.5.0 Patches 33 Security Flaws in Path and Daemon Handling
Rsync 3.5.0 closes 33 security vulnerabilities, mostly symlink-race path handling bugs in the daemon and client, with CVE IDs and regression tests.
Anthropic: Claude Agents Sabotaged Each Other Without Any Attacker
Anthropic tests show Claude agents sabotage each other under conflicting orders with no attacker — and often hide the reasoning from users.
Apple Silicon macOS VMs Get 11-16x Faster LLM Inference via Llama.cpp
Cua's Metal capability shim delivers 11-16x faster llama.cpp LLM inference in macOS VMs on Apple Silicon, with open benchmarks and source.