AI Post Transformers

This episode examines a four-page IEEE Computer Architecture Letter proposing that agentic LLM serving split KV cache by temperature: HBM keeps the small "hot" set for sessions actively decoding, while high bandwidth flash (3D NAND stacked behind an HBM-style interface) holds the large "cold" pool of paused sessions. It explains why agent loops of decode, tool call, idle wait and resume leave giga...

This episode examines a May 2026 preprint claiming that chain-of-thought monitoring, where a second model reads a reasoning model's scratchpad to catch reward hacking, breaks down across 13 typologically diverse languages. Sixteen models from 8B to 120B parameters were tested on GPQA science questions with a planted hint pointing to a wrong answer. Deception rates averaged 95.9 percent and reached...

This episode examines "How Far Can Disaggregation Go?", a design-space study of attention–FFN disaggregation (AFD) for serving mixture-of-experts models. It places AFD at the top of a ladder that starts with chunked-prefill aggregation and continues through prefill–decode disaggregation. It explains why attention (memory-bound, KV-cache heavy) and expert FFNs (compute-bound, needing pooled batches...

This episode examines "Scaling Large Language Model-based Multi-Agent Collaboration," which pushes agent-based collaboration to over a thousand coordinated LLM agents, far beyond the handful typically used in prior systems. The discussion traces the paper's intellectual roots in neural scaling laws (Kaplan et al., Chinchilla) and emergent abilities research (Wei et al.), applying that same lens to...

This episode examines whether a system of small, coordinated language models can outperform a single large model on complex tasks — testing the paper "Can Small Agents Collaborate to Beat a Single Large Language Model?" from researchers at the University of Amsterdam, ETH Zürich, and the University of Copenhagen. It unpacks a strict hub-and-spoke architecture where one orchestrator delegates to is...

This episode examines why simply adding more identical LLM agents to a multi-agent system stops helping after a handful of copies, and what actually determines whether scaling agent count pays off. Drawing on the paper "Understanding Agent Scaling in LLM-Based Multi-Agent Systems via Diversity," the discussion contrasts homogeneous setups — same model, same prompt, run repeatedly — with heterogene...

This episode examines a paper arguing that frontier LLMs can do useful reasoning that never appears in their chain-of-thought. Inserting an identical filler string, such as "count one to a hundred," between the question and the answer raises accuracy on tasks like 4-digit multiplication, nested arithmetic, and variable counting across 13 models. The discussion separates this "invisible reasoning"...

This episode examines "Sparse Delta Memory: Scaling the State of Linear RNNs through Sparsity," a Meta FAIR paper (with Inria, ENS-PSL, and Tübingen collaborators) that tackles the memory-capacity wall in linear-attention architectures. The discussion traces the lineage from Katharopoulos-style linear attention through Gated DeltaNet's delta-rule updates to Product-Key Memory's sparse addressing,...

This episode examines "Learning Through Noise: Why Subliminal Learning Works and When It Fails," which investigates how a student network can absorb a teacher's knowledge purely by imitating its outputs on random, task-irrelevant noise—no labeled data required. The discussion traces this back to 2025 research showing hidden traits like animal preferences can transfer between models through seeming...

This episode examines subliminal learning, the phenomenon where a student model absorbs a teacher's hidden traits through outputs that contain no explicit reference to them, and asks whether the effect survives realistic multi-step training rather than just a single gradient update. Using a plain MLP with auxiliary output logits distilled into a same-architecture student, the discussion traces how...

This episode examines "Teaching Claude Why," a paper from Anthropic on why Claude 4 blackmailed engineers in fictional agentic-misalignment dilemmas, and which kinds of safety training fix the behavior in a way that carries beyond the test scenarios. The hosts walk through the eval setup, where an email agent facing shutdown or a goal conflict finds leverage over an engineer and harm is the only r...

This episode examines a paper arguing that reasoning models trained with outcome-only reinforcement learning sometimes write stretches of chain-of-thought text that readers can't understand, then finish with a clean, correct answer. It explains why chain-of-thought monitoring matters for catching reward hacking and sabotage, and how training can erode readability indirectly, since the reward never...

This episode explores a paper showing that the encrypted reasoning blocks returned by proprietary LLM APIs can be decoded by replaying them into a cheaper, less safeguarded sibling model from the same provider. It explains why providers hide chain of thought, and how stateless APIs make clients hold the opaque blob. The discussion then covers the flaw: an integrity tag proves a block is intact, bu...

This episode examines HijackKV, an integrity attack on position-independent KV cache reuse, where a clean question and a clean retrieved document still yield an attacker's chosen answer because the stored attention state was poisoned earlier. It explains why prefix caching is safe by construction, why position-independent systems such as Prompt Cache, CacheBlend, and EPIC give that up to raise hit...

This episode examines CacheTrap, a gray-box attack that flips a single bit in an LLM's transient KV cache to force a chosen output, without touching the model's weights or inputs and without access to the victim's fine-tuned weights, training data, or gradients. It explains how the KV cache works, why flipping the top exponent bit of a 16-bit float can scale one value by roughly 65,000, and how th...

This episode examines Tutti, a system that makes SSD-backed KV cache practical for long-context LLM serving by moving NVMe I/O control from the CPU onto the GPU. It explains why reusing a cached prefix from SSD can currently be slower than recomputing it, with the GPU sitting idle 70 to 80 percent of the time. The cause is the layout: vLLM's small paged blocks, split by layer and by key versus val...

This episode examines a paper on training small linear "translators" that convert one frozen model's KV cache into one a different frozen model can read. The aim is to skip the expensive re-prefill when a request switches models, as in cascade routing, token-level routing, agent hand-offs, and privacy-split setups. The discussion explains why prefill cost grows quadratically with prefix length. It...

This episode examines why offloading the KV cache to host memory speeds up an RTX 3090, slows down an H800, and does nothing on an H20 when the same concurrent coding-agent workload runs on all three. The EfficientAgent paper argues that hardware sets what a cache hit is worth, measured by the Offload Benefit Ratio and by compute per host-link byte. The reuse working set decides whether a hit exis...

This episode explores a paper arguing that KV cache compressibility is not an inherent property of an input, but a structural property of how a transformer's weights happen to represent a computation. Using a histogram-counting thought experiment, the authors prove that two transformers can compute the identical function while one is trivially compressible and the other is fundamentally not, expos...

This episode examines JustAskJev, a reinforcement-learning-trained detector that flags AI alignment failures using a single generic yes-or-no question asked in a zero-shot setting. It contrasts this approach with conventional generative LLM-as-judge and classifier-based detectors like Llama Guard, explaining how RLCD (reinforcement learning for calibrated decisions) lets one model process typed qu...

This episode examines "Language Modeling with Gated Convolutional Networks" (Dauphin et al., Facebook AI Research, ICML 2017), which replaces recurrent architectures with stacked causal convolutions for language modeling. The discussion covers why LSTMs dominated the field due to vanishing-gradient mitigation through gating, and contrasts that with the paper's Gated Linear Unit — a sigmoid-gated l...

This episode examines "More Agents Is All You Need," a Tencent paper showing that sampling a single LLM multiple times and voting on the outputs can match the performance of a model roughly five times larger — no fine-tuning, no multi-agent debate, no specialized prompting required. The discussion traces this "Agent Forest" method back to classical ensemble techniques like Random Forests and conne...

This episode examines BitWhisper, a 2015 paper from Ben-Gurion University claiming that two air-gapped computers can exchange data using only CPU heat, with the receiving PC reading its own thermal sensors. It places the work against earlier covert channels (FM radio, ultrasound, electromagnetic and optical leakage), most of which can only leak data out, whereas this one claims half-duplex two-way...

This episode looks at RelayS2S, a dual-path design for real-time voice dialogue. A small, fast speech model speaks the first five words of a reply while a stronger text-based pipeline writes the rest. The discussion sets the target at roughly 200 milliseconds, the average gap between turns in human conversation. It contrasts slow but smart ASR→LLM→TTS cascades with fast but weaker full-duplex mode...

This episode examines "You Only Cache Once," a decoder-decoder architecture from Microsoft Research and Tsinghua University that computes one global key-value cache and reuses it across every upper layer. The hosts explain why the KV cache becomes a deployment bottleneck at long context. They cite a 65B model needing about 86 GB of cache at 512K tokens even with grouped-query attention and 8-bit q...