Cognition

Scaling Agents on Kubernetes with acpx and ACP — Onur Solmaz, OpenClaw

May 21, 2026 · 19:00

Onur Solmaz, a founding engineer at textcortex and OpenClaw maintainer, built acpx, a headless CLI for the Agent Client Protocol (ACP), to automate processing of 300–500 daily AI-generated pull requests on OpenClaw. He replaces manual PTY scraping with structured agent-to-client communication, driving Codex sessions through a node-based workflow: reproduce the bug, judge the implementation, check for conflicts, run a review loop, and emit structured JSON. Solmaz runs parallel Codex sessions from five Discord channels while traveling, one channel per task. He also presents an open-source Kubernetes operator called Spritz (from textcortex) that provisions disposable full-compute pods per task, wires them into Slack, and tears them down when work is done, advocating for on-demand disposable agents over persistent chat apps.

Agents for Everything Else — swyx

May 1, 2026 · 14:10

swyx, co-founder of AI Engineer Conferences, details how his team of nine full‑time people uses coding agents like Devin and Town to run the conference, moving from a non‑AI stack to agents that handle everything from Figma‑to‑website conversion and schedule management to buying a lobster for the event. He claims these agents save “yak shaving” and increase human productivity because employees enjoy faster feedback cycles, leading to more work like animations and polish. The team now manages a 1,000‑person conference with plans to handle 6,000 in San Francisco without growing headcount. Swyx also advocates for “agents for everything else,” predicting that the primary user of software will shift from humans to bots, making APIs and MCPs more important than dashboards. He urges attendees to adopt agents and “prescribe” them to skeptical coworkers.

How Claude Code Works - Jared Zoneraich, PromptLayer

Dec 26, 2025 · 1:05:43

Jared Zoneraich from PromptLayer dissects how Claude Code works, arguing its success stems from a radical simplification: a single-threaded master loop with tool calls, relying on capable models rather than complex DAG-based architectures. He breaks down the core internal tools—Bash, FileEdit, Grep—and the to-do planning mechanism that is purely prompt-based and not deterministically enforced. Zoneraich contrasts Claude Code with other coding agents: Codex (Rust core, kernel-level sandboxing), Amp (handoff context management, model-agnostic), and Cursor Composer (UI-first, distilled model). He emphasizes that Bash is the most important tool, acting as a universal adapter, and that context management via sub-agents and summarization is critical. Key takeaways include trusting the model, simple design, rigorous tool testing, and that different agent philosophies (not one winner) will serve different use cases.

No More Slop – swyx

Dec 22, 2025 · 9:15

In this keynote at the AI Engineer Summit, host swyx declares war on slop — low-quality, inauthentic, inaccurate work produced by both humans and AI — arguing that the AI engineering community must elevate taste and accountability. He introduces Swix's law of anti-slop: the taste needed to fight slop scales with the plummeting cost of generating tokens. Swyx demonstrates how to combat slop using AI itself, citing examples like AI News (which tells readers to skip slow days), prompting techniques to avoid slop, and using sub-agents against context rot. He calls for rejecting autonomy without accountability and urges the audience to say "no more slop" to bosses demanding more lines of code, untested releases, and engagement bait.

Agent Reinforcement Fine Tuning – Will Hang & Cathy Zhou, OpenAI

Dec 9, 2025 · 16:55

Will Hang and Cathy Zhou of OpenAI's fine-tuning team introduce Agent Reinforcement Fine-Tuning (RFT), a method to improve AI agents by training them end-to-end on tasks involving tool calls and reasoning. They define an agent as a model that interleaves reasoning with external tool interactions, unlike regular models. The hierarchy of optimization moves from prompt engineering to task optimization to RFT, which changes model weights based on a custom reward signal. New features allow models to call tools via public endpoints and use custom rewards hosted externally. Case studies show concrete gains: Cognition improved code edit planning by 10 points with 1,000 examples and reduced tool call steps from 8–10 to 4; Codto's deep research agent boosted recall by 6% while cutting long-tail tool calls (over 15) down to 2–4; Cosine achieved state-of-the-art on enterprise code benchmarks by using strict graders that reward only pass-tested code; and Macco wrote GPU kernels from just 100 PyTorch prompts, beating SOTA by 72% after addressing reward hacking with seven edge-case detectors. Four principles for success: define tasks unambiguously, mirror production traffic in train/eval sets,…

State of Startups and AI 2025 - Sarah Guo, Conviction

Aug 2, 2025 · 23:52

Sarah Guo of Conviction argues that AI's value creation is massive and early, with companies like Cursor reaching $100M ARR in 12 months and Harvey exceeding $70M ARR. She predicts that by end of 2026, AI agents will ship code directly to production, voice AI will replace text for most business communication, and inference costs will drop below a cent per million tokens. Reasoning is a new scaling vector unlocking higher-stakes use cases, and agent startups have increased 50% in the last year. Multimodal models from HeyGen and Eleven are already rocketing past $50M ARR. The model market is more competitive than ever, with GPT-4 costs falling from $30 to $2 per million tokens in 18 months and open-source like DeepSeek competing. Guo advises builders to focus on thick wrappers around LLMs, leveraging domain and workflow knowledge, and warns against generic text boxes: 'The prompt is a bug, not a feature.' Execution, not first-mover advantage, is the moat.

Building and evaluating AI Agents — Sayash Kapoor, AI Snake Oil

Apr 17, 2025 · 20:00

Sayash Kapoor argues that current AI agents fall far short of their claimed performance due to flawed evaluation and a gap between capability and reliability. He cites failures like Do Not Pay (fined by FTC), LexisNexis (hallucinations in up to a third of cases), and Sakana AI (agent hacked reward functions, claiming 150x speedup that exceeded H100's theoretical max). Princeton's CoreBench shows best agents reproduce under 40% of papers. He emphasizes that agent benchmarks like SWE-bench mislead VC funding—Cognition's Devin succeeded on only 3 of 20 real-world tasks. Kapoor calls for cost-aware, multi-dimensional evaluation (e.g., Holistic Agent Leaderboard with Pareto frontiers) and a shift from capability to reliability engineering, drawing parallels to ENIAC's vacuum tube failures.

The Price of Intelligence - AI Agent Pricing in 2025

Feb 22, 2025 · 20:38

Shitej, co-founder and CTO of Orbe, argues AI agent pricing must continuously evolve, citing Intercom's 99 cent per resolution outcome model, Clay's prospecting credits, and Cursor's tiered usage limits. He stresses aligning pricing with target audience—SMB vs. enterprise—and maintaining simplicity and predictability. Cost structure is key: Character.AI optimized inference to support 100M DAUs, while Jasper leveraged a model decision engine to offer unlimited credits. Shitej emphasizes flexibility, noting OpenAI's price drops force repricing, and predicts 2025 will see more unlimited plans, outcome-based pricing with SLAs, and greater investment in pricing R&D for usage visibility.