Open-Ended Evolution: A Reading Guide | Stanford CS329A Lecture 7
Open-ended evolution changes agent code and workflows; archives preserve branches, while held-out tests assess generalization.
ai
1239 postsSoftware Engineering Agents: A Reading Guide | Stanford CS329A Lecture 13
Program candidates need requirement-based counterexamples; speed matters only after correctness checks pass.
Agent Memory: A Reading Guide | Stanford CS329A Lecture 14
Retrieval, trained KV representations, and cache reuse address different bottlenecks; speed does not guarantee freshness.
Spotify Technology: Internal Developer Tools, Now Packaged as a Brand for Other Companies
On 2026-10-07 Spotify grouped Confidence, Portal, Xirp and its Backstage plugins under one brand, Spotify Technology. Its bet: once AI makes code cheap, judgment becomes the bottleneck and shared organizational context becomes the asset. Revenue is undisclosed; Confidence has public pricing and a free plan; Xirp is a macOS-only beta.
Train-Time Improvement: Turning Feedback into Learning | Stanford CS329A Lecture 6
Useful training feedback must distinguish candidates; filtering, relative advantages, and sampling determine the learning signal.
Search and Deep Research: Selecting a Deliverable Answer | Stanford CS329A Lecture 8
Candidate search selects solutions; retrieval fills knowledge gaps. Both require specifications and checkable evidence.
Long-Horizon Evaluation: Completion, Correctness, and Deliverability | Stanford CS329A Lecture 17
Human task duration, artifact quality, and citation support measure different things; evaluate both execution and deliverables.
Future Research: Turn Improvement Bottlenecks into Testable Hypotheses | Stanford CS329A Lecture 20
Diversity, verification, task selection, and efficiency are distinct bottlenecks; experiments need holdouts and falsifiable hypotheses.
Reinforcement Learning Systems: Connecting Inference and Training | CMU 11-768 Lecture 12
An RL system samples with an inference engine, assigns rewards through verification, recomputes logprobs and gradients in a trainer, then synchronizes new weights back to inference. Walk through these five stages in an invented example before examining caching, preserved histories, and asynchronous updates.
Agent Safety — Four Threat Models and Three Limits: Sandboxes, Credential Brokering, Monitoring | CMU 11-768 Lecture 13
Lecture 13 is about limiting what agents can access and do. The slides open with five real incidents, sort them into four threat models (malicious user, prompt injection, agent error, improper means), then give four layers of defense: red teaming and safety training, sandboxes and credential brokering, monitoring, and safety evaluation. The easiest point to miss: hiding the API key does not stop an agent from misusing the access behind it.
OpenHands — A Coding-Agent Framework That Went from Research Prototype to Thousands of Automated Runs | CMU 11-768 Lecture 14
Graham Neubig uses OpenHands, which he leads, to explain framework design: how coding agents evolved from HumanEval, SWE-bench and Devin to 2026's long-running, interruptible, parallel work; the parts of the Software Agent SDK (LLM, tools, conversation, condenser, workspace, confirmation policy); the single- vs. multi-agent trade-off; local vs. cloud and four interfaces (IDE, GUI, CLI, integrations); automations wired to issues and PRs; and revising skills from past trajectories.
pplx-embed-v2-late: An Open Late-Interaction Model That Searches PDF Pages Without OCR
On October 7, Perplexity open-sourced two ColBERT-style multimodal embedding models (0.6B and 9B, MIT license) that keep one 128-dim vector per token, score with MaxSim, and search PDF page images directly. The 9B scores 92.4% on MADQA (self-reported, with a Gemini 3.5 Flash agent); the cost is an index that grows with document length.
Eleven Coding Agents, Source Code Read: Nobody Uses LangChain, Nobody Uses Vector Retrieval
An 83-page paper from Wavestone AI Lab dissects 11 coding harnesses, including Claude Code, Codex CLI, Gemini CLI and OpenClaw. Across roughly 4 million lines of code, none imports a general-purpose agent framework and none retrieves code with vector embeddings. If you are building or choosing an agent, you can follow the paper's 18 recommendations and start from one bash tool and one while loop.
Poteto's Trust Ladder: Let the Agent Verify Itself Before You Let Go
Cursor engineer Lauren Tan (poteto) says she merges roughly 2,000–2,500 PRs a month, a self-reported figure no one has audited. Her method is three moves: build a verification skill first, turn repeated mistakes into lint and type constraints, and sample-review after merge. The method transfers if your domain can be verified by code.
Uber's MCP Gateway: How to Run 800 MCP Servers
Uber runs one MCP Gateway for 800+ MCP servers and 5,000+ tools: a control plane crawls internal APIs into disabled-by-default tools, a data plane handles protocol translation, authorization and redaction, and Omni MCP, Response Projection and Code Mode keep context small at scale.
Pi Durable: Where a Long-Running Agent Picks Up After a Crash
Pi 1.0 and the experimental Pi Durable package shipped together in early October 2026. Pi Durable turns every model request, tool call and compaction into a task that writes a checkpoint, so a killed process resumes from its last checkpoint; Cloudflare followed with PiHarness on Durable Objects. The key design decision is classifying tools as safe or unsafe to replay.
AI Agent Interview Prep: From Tool Calling and Memory to MCP and Prompt Caching
Agent interviews keep returning to eight topics: the agent loop, structured output, function calling, large tool sets, memory, design trade-offs, MCP versus A2A, and prompt caching. This post strings them into one line (concept, mechanism, how to answer) and corrects when the 2026-07 MCP spec changes actually landed.
LLM Engineering Interview Prep: Fine-Tuning, Alignment, Inference Optimization, Evaluation, and Safety
Seven LLM engineering topics that come up often in interviews: LoRA/QLoRA and fine-tuning vs RAG, RLHF/DPO/GRPO alignment, inference optimization (PagedAttention gives vLLM 2-4x throughput), sampling and decoding, LLM evaluation, the OWASP LLM Top 10 (2026 edition), and hallucination. Each section covers the concept, the mechanism, and how to answer.
ML Basics and Transformer Internals: From Bias-Variance and AdamW to Attention, RoPE and MoE
Interview follow-ups usually land on mechanisms: why divide by √d_k, how AdamW differs from Adam plus L2, why a high AUC still isn't shippable. This post walks through concept, mechanism and how to answer, then ends with 3 runnable numpy exercises.
Prompt, Context, Harness: The Three Layers, Their Boundaries, and Evaluation Gates
Prompt engineering shapes a single instruction, context engineering decides what the model sees right now, and harness engineering wraps the whole non-deterministic system. Bsharat's 26 principles, Breunig's four context failures, and OpenAI's roughly one-million-line, zero-handwritten-code harness experiment each map to one layer. Evaluation is the piece teams skip most, and it belongs in a CI gate that blocks silent regressions.