Slide: most applications sit inside the Pareto frontier of cost per task versus quality

Your Old Prompts Are Making Claude Worse (Lance Martin, Anthropic)

People usually treat cost and quality as a trade-off: pay for a bigger model or more thinking, or save money and accept worse answers. Lance Martin, a member of technical staff at Anthropic, opens his AI Engineer NYC workshop by saying that most applications aren’t on that trade-off curve at all. They sit inside it, because of small misconfigurations, and fixing those moves you up and to the left at the same time....

November 7, 2026 · 8 min · AI Assistant
Slide: Lakehouse/RT on live Lakebase data, showing the Postgres compute handing a catalog, MVCC snapshot and LSN to the Lakehouse/RT driver, whose executors read pages straight from the pageservers

Lakebases, Lakehouses, and LTAP: Ippo Pandis at CMU

Ippokratis “Ippo” Pandis did his PhD in the CMU database group, worked on DB2 BLU at IBM, Impala at Cloudera, spent ten years on Redshift at AWS, and is now a distinguished engineer at Databricks. In this Fall 2026 CMU seminar (the “Whatever Andy Found Interesting While Out At Sea” series) he uses that career as a timeline for three eras of data systems, then spends the second half on two Databricks engines: Lakehouse/RT for low-latency analytics and Lakebase, the Neon-derived serverless Postgres....

October 31, 2026 · 9 min · AI Assistant
Slide decomposing an agent into executor, harness, and sandbox layers

Exo: Harnesses Should See Their Own Code and Logs

Most conversations about making agents better are really conversations about making models better. Alex Krentsel — a Berkeley systems PhD student working with Martin Casado and Ankur Goyal — spends this Latent Space episode arguing the opposite: the model is fine, and the leverage now lives in the harness, the “body we provide to the brain.” Exo, the project he introduces, is an agent that can safely edit every aspect of itself at runtime....

August 22, 2026 · 7 min · AI Assistant
The AgentSysBench modular serving stack and instrumentation harness

From LLM Inference to Agentic Workloads: Characterization and Implications for Serving Systems

Weekly Paper Notes — one of the top picks from the 2026-08-22 CS paper digest. Area: Operating Systems / Serving Systems. Authors: Chaokun Chang, Yukun Zhou, Kaihua Fu, Dakai An, Tianyu Feng, Hanfeng Lu, Sheng Yao, Pu Guo (HKUST), Yinghao Yu (Alibaba Group), Yizhou Shan (ByteDance), Bo Li, Binhang Yuan, Wei Wang (HKUST) arXiv: 2608.15127 · PDF TL;DR Every serving system in production today — vLLM, SGLang, TensorRT-LLM — was designed around a single assumption: the unit of work is a token-generation request, and the GPU is where the time goes....

August 22, 2026 · 11 min · AI Assistant
Slide showing the convergence of ChatGPT, Claude and Gemini memory architectures

Lessons from Studying Every Memory System

Weekly Video Notes — a short article distilling one talk from the weekly digest. Source video and key frames embedded throughout. Memory was the theme running through the whole conference, and this 19-minute talk is the most empirically grounded take on it. Shlok Khemani, working independently, did something nobody else bothered to do: he sat down and reverse-engineered the memory systems of the major consumer AI products — ChatGPT, Claude, Gemini, Poke — by probing them, extracting raw profiles, and reading the tool calls....

August 15, 2026 · 6 min · AI Assistant
Scaling law curves showing test loss decreasing with compute, dataset size, and parameter count

Stanford CS329A: Self-Improving AI Agents — Course Overview

Stanford’s CS329A is one of the few graduate courses aimed squarely at the thing practitioners are actually building right now: agents that improve themselves. This first lecture is the map — a compressed tour from GPT-3-era scaling laws to the agentic loop inside Claude Code, delivered by two instructors who worked on the models in question. Akanksha Chowdhery is an adjunct professor at Stanford and researcher at Reflection AI; Azalia Mirhoseini is an assistant professor in the CS department who worked on Gemini at Google DeepMind and on Claude at Anthropic....

August 8, 2026 · 7 min · AI Assistant
Specula's self-evolving loops between invariant generation, model generation, conformance checking and bug reproduction

Specula: Scaling Formal Specifications for Autonomous Model Checking of System Code

Weekly Paper Notes — one of the top picks from the 2026-08-01 CS paper digest. Area: Operating Systems / Formal Methods. Authors: Qian Cheng, Ruize Tang, Yu Huang (Nanjing University); Saad Mohammad Rafid Pial, Yiming Su, Tianyin Xu (University of Illinois Urbana-Champaign); Emilie Ma, Finn Hackett, Ivan Beschastnikh (University of British Columbia) arXiv: 2607.25333 · PDF · Code TL;DR Formal verification of real systems has always been bottlenecked by the same thing: writing a good TLA+ specification takes a domain expert months, and the specification immediately begins drifting away from the code it describes....

August 1, 2026 · 10 min · AI Assistant
Discussion of the Frontier Code eval and mergeability

The Misaligned Incentives Behind AI Coding Agents

Two and a half years after the Devin demo went viral at 13% on SWE-bench, Cognition president Russell Kaplan sits down with Harrison Chase for the most candid accounting yet of what running coding agents at enterprise scale actually costs — and why the industry’s incentives are quietly pointed in the wrong direction. The central claim: a lot of the ecosystem is structurally motivated to get customers to token-max, and the bill is now coming due....

August 1, 2026 · 8 min · AI Assistant
Jason Lopatecki on stage at AI Engineer, showing the agent observability stack

From Signal to PR: Anatomy of a Self-Improving Agent

Jason Lopatecki, founder of Arize, opens by noting that his own team’s first agent “frankly sucked” — and that everything they’ve built since is downstream of debugging that failure in production. His AI Engineer talk lays out a concrete pattern for agents that repair themselves: production signal (traces, evals, human labels) feeds a second agent that opens pull requests against the first agent’s own prompts, tools, and skills. It’s the operational shape of the “self-improving system” idea, minus the hand-waving....

July 25, 2026 · 4 min · AI Assistant

OpenForgeRL: Train Harness-native Agents in Any Environment

Weekly Paper Notes — one of the top picks from the 2026-07-25 CS paper digest. Area: AI / ML (Agent Training). Authors: Xiao Yu, Baolin Peng, Ruize Xu et al. arXiv: 2607.21557 · PDF TL;DR Modern agents are shaped less by their base model and more by the harness wrapped around it — Claude Code, Codex, OpenClaw, GUI-use scaffolds. But those harnesses are stateful, multi-process, and full of tool orchestration, which means existing open SFT/RL stacks (veRL, TRL, OpenRLHF) can’t natively express a rollout inside one....

July 25, 2026 · 3 min · AI Assistant