AI Explained
Plain explanations of trending AI concepts, with live visualizations.
SwitchSD reads copy intent from the model's own states — Copy-intent probe drafting-mode switch — What does it mean?
SwitchSD reads copy intent from the target model's hidden states, switching to cheap copying only when the probe predicts real repetition.
NVIDIA replaces GenAI-Perf with multiprocess AIPerf — Multiprocess load generation — What does it mean?
A single-process benchmark client is capped by Python's GIL, so the throughput you measure can be the client's ceiling, not the server's.
Let models trigger full attention only when recall helps — On-Demand Attention recall-head gating — What does it mean?
A small recall head decides, per decode step, whether reading the full KV cache is worth it — at long context, skipping it cuts decode cost.
DeepSeek-V4.1-Flash runs prefill on 8B parameters and decode on 16B — Causal Encoder-Decoder — What does it mean?
DeepSeek-V4.1-Flash runs prefill on an 8B parameter path and decode on a 16B one — a split in the parameters, not in the machines.
Chronicle replays agent incidents as CI tests — Cut-point replay vs stubbing every boundary — What does it mean?
Freeze the boundaries you are not testing, run the one you are live, and an incident becomes a CI test.
D-Quant drifts variable-length KV codes into fixed-size token streams — Entropy-coded KV cache — What does it mean?
Short codewords for common KV values, long for rare ones, then drifted back into fixed-size per-token streams.
Magenta closes informal math reasoning with Lean-guided repair — Error-attribution routing — What does it mean?
Magenta names why a Lean proof failed, then routes the retry to a re-derivation or a one-step patch instead of resampling.
TypeSafe releases Jev — Typed parallel decisions — What does it mean?
Jev fixes the output type before it runs, samples every field in parallel, and attaches a calibrated probability to each one.
JustFit serves a 212,992-token context on a 24 GiB laptop — Just-in-time state residency — What does it mean?
JustFit holds a 212,992-token context on a 24 GiB laptop by scheduling when each piece of state is resident, not by shrinking the weights.
Devin-built GPU sieving factored RSA-260 — Preemptible sieving vs the interconnect-bound solve — What does it mean?
Sieving survives on preemptible GPUs because losing a unit costs milliseconds. The block Wiedemann solve cannot, so only it pays for NVLink.
Emergence World runs 16-day agent worlds — Non-compositional alignment — What does it mean?
Eight 10-agent worlds, 16 days, no survivors: agents detected the injection and still acted on it up to 46 hours later.
GAUGE finds 57.5% of agent chats rated satisfying still failed the user's task — Ranking validity vs construct validity — What does it mean?
An offline judge can rank agents right and still measure the wrong thing: 57.5% of chats rated satisfying failed the user's task.