• Simon Willison built Battle Drones through 12 major iterations and 321 agent commits, mainly by Claude Code; although he knew little TypeScript and reviewed almost none of the code, he playtested it extensively Simon Willison’s Newsletter. For a major gameplay revision, he prompted Claude Opus 5.5 with “Make it a LOT more fun” in Ultracode, a dynamic workflow that orchestrates many subagents; the overnight run included more than 1,000 simulated playtests Simon Willison’s Newsletter. In 1,200 Normal AI-vs-AI matches, games still undecided after 25 minutes fell from 14% to 0.9%, while wins by sides that had been 800+ scrap behind rose from 24% to 46% Simon Willison’s Newsletter.
• When the game’s AI ignored infantry and troop-carrying Condors, Willison turned that observation into a design brief: specify the strategic incentives and map constraints, then have the agent research and critique the design before building, with changes agreed first Simon Willison’s Newsletter. The resulting Archipelago map had seven uplinks capturable only by flying infantry in a Condor, and Willison described it as the game’s most fun map Simon Willison’s Newsletter.
• To add audio multiplayer, he pointed Claude Code at his working Chirp Pong proof of concept and asked it to adapt the approach; Claude built a Radio Probe to measure bandwidth before implementing an audio modem Simon Willison’s Newsletter. He had not extensively tested the feature, though it seemed to work across laptops, iPhones, and iPads; after a player got a headache from the high-pitched sounds, he added a warning and moved toward online multiplayer, using a stateless WebSocket relay after WebRTC failed between his devices Simon Willison’s Newsletter.
• The Claude Code team at Anthropic describes a review workflow in which Claude reviews and fixes most changes before a human reviewer is asked to focus on higher-level questions; it frames review around what could go wrong and which automated or human check can catch it, rather than whether a human read every line Simon Willison’s Newsletter. As a complementary enforcement technique, Geoffrey Huntley described a pre-commit hook that checks diffs for direct calls bypassing a diagnostics library, fails the commit, and injects a prompt telling the agent to use the library—avoiding reliance on instructions that can drift Simon Willison’s Newsletter.

• DeepSeek open-sourced DeepInfer, the production inference framework used for V4.1 Flash, with distributed inference, speculative decoding, SWA Bounded Replay and structured output; it runs on NVIDIA and Huawei Ascend and includes the deepseek-recipe API/token conversion component. KVCache management and load balancing are not fully open-sourced. @latentspacepod
• Agent-serving cache pattern: retain reusable Block KVCache prefixes in shared 3FS storage. DeepSeek reports a 3-day TTL for agent traffic; shared storage lets any prefill machine hit any prefix without prefix-affinity routing, reducing repeated prefill work. @latentspacepod SWA KV remains in machine memory (about 180 seconds’ TTL and over 98% hit rate); on a miss, SWA Bounded Replay recalculates only the latest 128 tokens to rebuild it. @latentspacepod
• deepseek-recipe maps prompt-builder-inserted special tokens to token IDs and treats user/tool text that merely resembles them as ordinary text, preventing token injection; it also parallel-encodes ordinary-text segments between known special-token boundaries to reduce long-context tokenization latency. @latentspacepod DSpark allocates speculative-token validation according to per-token confidence; DeepSeek reports 6% higher online throughput than fixed five-token validation. @latentspacepod

• For an agent-visible personal workspace, he used a Markdown to-do's.md file as the shared data layer and synced it to a web app every 10 minutes; he and his agent could edit it from different devices, and access was restricted to approved email addresses. Ben Tossell (Ben's Bites)
• To keep build requests from interrupting his personal-agent conversations, he set up a separate builder, Bill, as a new thread using workspace instructions; the personal agent can pass build requests to Bill, and he finds agents better at prompting one another than he is. Ben Tossell (Ben's Bites) For review, he asked subagents to test desktop and mobile, check for bugs, and perform a thorough review, then had the agent fix the reported issues. Ben Tossell (Ben's Bites)
• In BB, he uses Codex, Claude, Factory, and Pi; for UI exploration, a prototyping scale generated three alternatives that he mixed and refined with a simple request for a Linear-like feel, producing features such as a Kanban board and alternate detail views. Ben Tossell (Ben's Bites) He also uses Executor to connect services and tools once, then gives its setup prompt to an agent so the connected tools can be used across workflows. Ben Tossell (Ben's Bites)

• Omarchy is designed as an agent-ready Linux desktop: agents are preconfigured so users can start making a theme, app, or plugin from an invitation to “make something cool.” GOSIM Foundation DHH’s stated setup target is a computer ready to use in 30 seconds, rather than spending half an hour or half a day configuring a developer machine. GOSIM Foundation
• He says he used a model he names “Kim E K25” as his primary driver for over a month, praising its 200 tokens per second versus 30–40 tokens per second for frontier models at the time. GOSIM Foundation

• Simon Willison built Battle Drones through 12 major iterations and 321 coding-agent commits, mainly with Claude Code; he reviewed almost none of the TypeScript code but playtested extensively. He found static HTML/JavaScript with WebGL, Phaser, and Three.js effective platforms for agent-built games. Simon Willison's Weblog: Entries
• For a stalled gameplay problem, he gave Opus 5.5 the blunt prompt “Make it a LOT more fun” using Claude Code’s Ultracode dynamic workflows, which orchestrate multiple subagents. The overnight run included more than 1,000 simulated playtests; in 1,200 AI-vs-AI matches on Normal, games still undecided after 25 minutes fell from 14% to 0.9%, while wins by a side that had been 800+ scrap behind rose from 24% to 46%. Simon Willison's Weblog: Entries
• When infantry and troop-carrying Condors lacked a strategic role, he prompted Claude to design a map around that problem and explicitly requested research and critique before implementation, with agreement on modifications before building. The resulting Archipelago map made seven island uplinks capturable only by flying infantry there in a Condor. Simon Willison's Weblog: Entries
• To add audio multiplayer, he pointed Claude Code at his working Chirp Pong proof of concept, then had it build a Battle Drones version. Claude created a Radio Probe to measure device bandwidth before implementing a full audio modem; Willison reported successful trials between laptops, iPhones, and iPads, while cautioning that testing was still limited. Simon Willison's Weblog: Entries
• For replay and multiplayer, use a deterministic simulation: tiny differences in browser implementations of Math.sin() and Math.cos() caused desynchronization, so Claude replaced them with custom versions. Simon Willison's Weblog: Entries

• For this add-on, the host treated model choice as secondary: a capable Codex setup was likely enough, while Opus was described as more correct but much more expensive. ThePrimeTime Cursor was recommended as an approachable interface for building without relying on the terminal. ThePrimeTime
• Keeping the project folder pointed at the WoW add-on folder made changes testable with a game reload; the host also recommended initializing Git. ThePrimeTime Local-only version control was considered workable, but a remote copy would help if switching computers or losing the machine. ThePrimeTime
• Check platform capabilities before settling on a feature: in this WoW add-on exploration, the investigation found no general HTTP/socket or arbitrary file access, and detailed combat-log events were restricted. ThePrimeTime
• Use a review gate before implementation: the host avoids formal plan mode but has agents discuss their approach and answer questions before he authorizes coding, because their eventual implementation can differ from what he expected. ThePrimeTime
• Build and verify in small increments: the first generated legacy-menu dropdown reused an existing screen, so the pair tested it in-game and refined the request; the host recommends starting small and working one step at a time. ThePrimeTime
• The host said dictating ideas on his phone while pacing worked better for him than typing, which could not keep up with his thoughts. ThePrimeTime He also said agent-assisted coding had become better than his hand coding for completing tasks, while manual coding still produced better quality and thoughtfulness; with implementation less of a barrier, idea and design quality remain limiting factors. ThePrimeTime

• Tenex’s “meta harness” pairs structured repository documentation with a CLI that agents use for plans, visualizations, client readouts, and other parts of the engineering process; its canonical plan has become less prescriptive as models improved. Latent Space Agents log decisions and activity, check the artifacts into Git, and keep the context for why decisions were made alongside the code as a durable record. Latent Space
• The team’s current model preference is Opus 5.5, with Codex still useful for computer-use tasks and for reviewing Opus’s work; engineers report the back-and-forth produces the best results. Latent Space One engineer uses AMP’s cloud “orbs” to run work off his computer and have another orb review Opus’s output; he says a newly added subscription hookup cuts costs by about 80%. Latent Space
• Tenex reports roughly doubled engineer output over the period discussed, tracks average story points per engineer per month, and re-evaluates story-point criteria and project estimates at least quarterly as models improve. Latent Space

• DeepSeek open-sourced DeepInfer, its large-scale inference framework for V4.1 Flash. It supports distributed inference, speculative decoding and structured output, and runs on NVIDIA and Huawei Ascend hardware. @latentspacepod
• DeepSeek Recipe handles encoding and decoding between mainstream LLM API protocols and model tokens, with processing aligned to DeepSeek’s official API for third-party deployments. @latentspacepod For agent-serving systems, DeepSeek identifies prefix KVCache reuse as a way to cut repeated prefill as contexts grow; its stated agent-traffic cache TTL is 3 days. @latentspacepod Its persistent Block KVCache is stored on 3FS, while SWA KVCache stays in machine memory and has a reported ~180-second TTL and over 98% hit rate. @latentspacepod
• Caveat: DeepInfer’s KVCache-management and load-balancing components are coupled to DeepSeek’s internal infrastructure and are not yet fully open source. @latentspacepod

Sanfilippo describes DeepSeek Infer as a cloud inference engine for DeepSeek V4.1 Flash, built from a vLLM fork and ideas from other engines; its key design choice is specializing kernels for a particular model rather than maintaining a general-purpose engine. Salvatore Sanfilippo The release targets SM100/B200-class Nvidia and Huawei accelerators, but is incomplete for some serving needs: KV-cache management is withheld as a proprietary advantage, and prefill/generation separation for microbatching is not included. Salvatore Sanfilippo For local deployment, he cautions that kernels tuned for SM100 do not transfer directly to DGX Spark’s SM121 architecture and are optimized for heavy batching; he may adapt selected parts only if they offer a benefit. Salvatore Sanfilippo

• After a CA-key leak, Huntley prompted an agent to check whether his NixOS fleet was affected. He used Nix’s single source of truth to patch transitive dependencies fleet-wide, then commit and autodeploy the fix. Geoffrey Huntley
• For a temporary workaround, he had the agent add an AGENTS.md reminder to reassess and back out the patch later. The reminder specified checking on or after Oct. 22 whether nixos-26.05 included nixpkgs commit 7816d39, checking again two days later if not, and removing the workaround once it was included—while retaining separate TLS and rustls-webpki changes. Geoffrey Huntley

Simon Willison built browser-based RTS Battle Drones mainly with Claude Opus 5.5; Claude also generated all of its Three.js 3D models, and a model explorer lists their animation states. @simonw +1

The game can pit two LLMs against each other by pausing every five seconds for them to assess the game state and queue commands; a replay pairs Claude Haiku 5.5 with GPT-6 Luna. @simonw The device-to-device audio multiplayer produced a persistent high-pitched noise, prompting a warning that it might cause a headache; Willison added online multiplayer using a small Fly.io-hosted WebSockets relay, so players can share a link to join. @simonw +1

• Tenex’s MetaHarness combines shared skills, structured project documentation and a CLI. Agents work from a canonical plan, log decisions and activity, and check the records into Git alongside the code—preserving the rationale and context needed to resume long-running work. Tenex cautions that this level of structure can be overkill for a small team on one project. Latent.Space
• As models can get to roughly 90% of a solution when given the right context, Tenex’s CJ says his work has shifted from coding toward drawing out customer context and providing it to the model. Latent.Space
• Tenex describes Opus 5.5 as the team’s usual model, with Codex used for computer-use tasks and review; the discussion also describes using AMP’s remote Orbs to switch models and review another agent’s work. Latent.Space
• Tenex reports engineering output roughly doubled over the period as models improved at long-running tasks, and says it reevaluates story-point criteria at least quarterly. Latent.Space

A TODO-board build was shared with a video and a post containing copy/paste instructions for agents, giving developers a starting point for trying an agent-assisted project. @bentossell

• Macroscope describes a PR-review workflow in which language-specific code “walkers” provide change context and team rules run as native GitHub checks that can block failing PRs. The workflow auto-approves a PR when it passes those checks and a code review and has a small blast radius; Macroscope says it now auto-approves 40% of customer PRs. Fireship
• For motion graphics, Claude can generate the code that renders a sequence instead of producing video with diffusion; having the code makes the result easier to customize and analyze. Fireship
• The video’s self-described “Trust Me Bro” benchmark roundup gives Gemini 4 Argon a mixed coding profile: it reports a lead on deep software engineering, but Claude Opus 5.5 scores 66 to 57 on Terminal Bench 4.0, GPT-6 Astra leads by more than 10 points on Frontier S, and Argon ranks ninth in webdev Code Arena. These are the video’s benchmark-specific claims, not a settled overall ranking. Fireship

For AINews reporting, swyx made Opus 5.5 the default after a side-by-side evaluation, praising its concise, tasteful writing and reduced “slopese” versus Opus 5 @swyx. He also cautioned that Opus’s writing quality can be undermined by unspecified “no-no words” in prompts, making it unsuitable for the critical path of his AI media organization @swyx.

• Theo built a custom Ubuntu-based environment for agents rather than his personal preferences: it is headless but can spin up XFCE-fork GUIs for agent computer use, and uses Bash instead of Zsh. He says over 30% of Claude’s errors across his machines came from Zsh newline formatting that led Claude to misformat ripgrep commands; he also found agents less capable on Arch and CachyOS dev boxes. Theo - t3․gg
• Choose the stack around agent throughput, not developer preference: Theo kept the React Native mobile app instead of pursuing his preferred SwiftUI rewrite because agents could work faster in the existing app; he says team performance work made it comparable to, or in some ways faster than, the alternative. Theo - t3․gg
• Theo reports that an AI-assisted Rust rewrite of the TypeScript compiler was working in under 20 hours, ran 2–3 times faster than TSGO, supported WASM, and achieved 99.99% accuracy against other TypeScript versions on the real projects he cared about. Theo - t3․gg

Peter Steinberger says his “claw” automatically mutes most replies he characterizes as “slop.” @steipete

Ben Tossell describes a custom workspace combining a Superhuman-like email experience with a Linear-style todo board; the email is built on Rhys Sullivan’s Executor. @bentossell His bot uses the workspace and can be tagged in comments; it also tracks domains, expirations, hosts, and linked local repositories, with plans to add links to mini-apps. @bentossell He shared a video and copy/paste instructions for agents explaining how he built it. @bentossell

ThePrimeagen says he dislikes Claude’s apparent preference for legacy versions “just in case.” @ThePrimeagen

The quoted post claims DeepSeek V4.1 Flash 1017 beat GPT 6 Sol on a multi-step offensive-cybersecurity task @Hesamation and says it can be run locally @Hesamation. Primeagen disputed the local-running claim, saying that even his “incredible setup” is far from sufficient to run it locally @ThePrimeagen.