Benjermin Franklin @bisforben2010

AI-native software engineering teams operate very differently than traditional teams. The obvious difference is that AI-native teams use coding agents to build products much faster, but this leads to many other changes in how we operate. For example, some great engineers now play broader roles than just writing code. They are partly product managers, designers, sometimes marketers. Further, small teams who work in the same office, where they can communicate face-to-face, can move incredibly quickly. Because we can now build fast, a greater fraction of time must be spent deciding what to build. To deal with this project-management bottleneck, some teams are pushing engineer:product manager (PM) some teams are pushing engineer:product manager (PM) ratios downward from, say, 8:1 to as low as 1:1. But we can do even better: If we have one PM who decides what to build and one engineer who builds it, the communication between them becomes a bottleneck. This is why the fastest-moving teams I see tend to have engineers who know how to do some product work (and, optionally, some PMs who know how to do some engineering work). When an engineer understands users and can make decisions on what to build and build it directly, they can execute incredibly quickly. I’ve seen engineers successfully expand their roles to including making product decisions, and PMs expand their roles to building software. The tech industry has more engineers than PMs, but both are promising paths. If you are an engineer, you’ll find it useful to learn some product management skills, and if you’re a PM, please learn to build! Looking beyond the product-management bottleneck, I also see bottlenecks in design, marketing, legal compliance, and much more. When we speed up coding 10x or 100x, everything else becomes slow in comparison. For example, some of my teams have built great features so quickly that the marketing organization was left scrambling to figure out how to communicate them to users — a marketing bottleneck. Or when a team can build software in a day that the legal department needs a week to review, that’s a legal compliance bottleneck. In this way, agentic coding isn’t just changing the workflow of software engineering, it’s also changing all the teams around it. When smaller, AI-enabled teams can get more done, generalists excel. Traditional companies need to pull together people from many specialties — engineering, product management, design, marketing, legal, etc. — to execute projects and create value. This has resulted in large teams of specialists who work together. But if a team of 2 persons is to get work done that require 5 different specialities, then some of those individuals must play roles outside a single speciality. In some small teams, individuals do have deep specializations. For example, one might be a great engineer and another a great PM. But they also understand the other key functions needed to move a project forward, and can jump into thinking through other kinds of problems as needed. Of course, proficiency with AI tools is a big help, since it helps us to think through problems that involve different roles. Even in a two-person team, to move fast, communication bottlenecks also must be minimized. This is why I value teams that work in the same location. Remote teams can perform well too, but the highest speed is achieved by having everyone in the room, able to communicate instantaneously to solve problems. This post focuses on AI-native teams with around 2-10 persons, but not everything can be done by a small team. I'll address the coordination of larger teams in the future. I realize these shifts to job roles are tough to navigate for many people. At the same time, I am encouraged that individuals and small teams who are willing to learn the relevant skills are now able to get far more done than was possible before. This is the golden age of learning and building! [Original text: deeplearning.ai/the-batch/issu… ]

@rebootgamer @FoxNews We're the bad guy 😢

@obi_j061595 @AP It's time for your generation to move on brother. We don't want war and we don't want kids growing up with bombs being dropped around them anywhere! We want peace, whatever the cost. I do at least

@FoxNews @pdoocy What's insane is how much we have xpect literally nobody to die on our side and when they do it is a failure. We shouldn't be there and war is maybe the worst thing about humans but people are going to die ... Planes are gonna get hit...

@thetobifaj @FoxNews @pdoocy Oh Iran wants that pilot. Maybe even more than US

@dirrtydre85 @realstewpeters I don't want Trump to fail or anyone to die. I understand your sentiment tho wish it wasn't him but I can't root for the other team 🤔

@elonmusk @grok how many crashed?

@alfred_pea42376 @HousebotGuy People who know things don't need to go around telling people they know things .. seems more like a strong hope

Most people think using Claude Code is about writing better prompts. It’s not. The real unlock is structuring your repository so Claude can think like an engineer. If your repo is messy, Claude behaves like a chatbot. If your repo is structured, Claude behaves like a developer living inside your codebase. Your project only needs 4 things: • the why → what the system does • the map → where things live • the rules → what’s allowed / forbidden • the workflows → how work gets done I call this: The Anatomy of a Claude Code Project 👇 ━━━━━━━━━━━━━━━ 1️⃣ CLAUDE.md = Repo Memory (Keep it Short) This file is the north star for Claude. Not a massive document. Just three things: • Purpose → why the system exists • Repo map → how the project is structured • Rules + commands → how Claude should operate If CLAUDE.md becomes too long, the model starts missing critical signals. Clarity beats size. ━━━━━━━━━━━━━━━ 2️⃣ .claude/skills/ = Reusable Expert Modes Stop repeating instructions in prompts. Turn common workflows into reusable skills. Examples: • code review checklist • refactoring playbook • debugging workflow • release procedures Now Claude can switch into specialized modes instantly. Result: More consistent outputs across sessions and teammates. ━━━━━━━━━━━━━━━ 3️⃣ .claude/hooks/ = Guardrails Models forget. Hooks don’t. Use hooks for things that must always happen automatically. Examples: • run formatters after edits • trigger tests after core changes • block sensitive directories (auth, billing, migrations) Hooks turn AI workflows into reliable engineering systems. ━━━━━━━━━━━━━━━ 4️⃣ docs/ = Progressive Context Don’t overload prompts with information. Instead, let Claude navigate your documentation. Examples: • architecture overview • ADRs (engineering decisions) • operational runbooks Claude doesn’t need everything in memory. It just needs to know where truth lives. ━━━━━━━━━━━━━━━ 5️⃣ Local CLAUDE.md for Critical Modules Some areas of your system have hidden complexity. Add local context files there. Example: src/auth/CLAUDE.md src/persistence/CLAUDE.md infra/CLAUDE.md Now Claude understands the danger zones exactly when it works in them. This dramatically reduces mistakes. ━━━━━━━━━━━━━━━ Here’s the shift most people miss: Prompting is temporary. Structure is permanent. Once your repository is designed for AI: Claude stops acting like a chatbot... …and starts behaving like a project-native engineer. 🚀

@WorkflowWhisper Layoffs

@Hadley @AnthropicAI This is what they always do what do you mean?

Our latest Claude Code hackathon is officially a wrap. 500 builders spent a week exploring what they could do with Opus 4.6 and Claude Code. Meet the winners:

10 processes, 7969 lines of code total. the smallest worker is 184 lines and handles all publishing. biggest is 3284 lines and organizes 16 types of meetings

Vox @Voxyz_ai

6 months ago

x.com/i/article/2023…

8 17 229 44K 537

RedShip just crossed 300 users 🤯 Honestly, that feels huge. In just 59 days: 👥 300+ users 💳 12 paying users 💰 $399 MRR Now it’s time to really market it. Next stop: $1,000 MRR 💪

@Zephyr_hg News

I've never felt this much behind as a programmer. The profession is being dramatically refactored as the bits contributed by the programmer are increasingly sparse and between. I have a sense that I could be 10X more powerful if I just properly string together what has become available over the last ~year and a failure to claim the boost feels decidedly like skill issue. There's a new programmable layer of abstraction to master (in addition to the usual layers below) involving agents, subagents, their prompts, contexts, memory, modes, permissions, tools, plugins, skills, hooks, MCP, LSP, slash commands, workflows, IDE integrations, and a need to build an all-encompassing mental model for strengths and pitfalls of fundamentally stochastic, fallible, unintelligible and changing entities suddenly intermingled with what used to be good old fashioned engineering. Clearly some powerful alien tool was handed around except it comes with no manual and everyone has to figure out how to hold it and operate it, while the resulting magnitude 9 earthquake is rocking the profession. Roll up your sleeves to not fall behind.

@sabir_huss50540 Solid list, saved ty

Meta just solved RAG's biggest bottleneck. 30× faster decoding. Zero accuracy loss. The problem nobody talks about: When you feed an LLM 80 retrieved passages, only 5-10 are actually useful. The rest? Dead weight. But you're computing attention for ALL of them. The math is brutal: Traditional RAG with 16K context: → 100+ seconds to first token → 10× throughput drop → Massive memory waste What REFRAG does: Compresses context chunks into single embeddings. Instead of processing 16,384 tokens → Process 1,024 chunk embeddings. The results: ✓ 30.85× faster time-to-first-token ✓ Zero perplexity loss ✓ 16× context extension (4K → 64K tokens) ✓ 3.75× better than previous SOTA Why it works: RAG contexts have sparse attention patterns. Most retrieved passages don't interact. REFRAG exploits this with: 1./ Precomputable embeddings - Cached from retrieval, reused across inferences 2./ RL-based compression - Smart policy decides what to compress 3./ Works anywhere - Unlike previous methods, compresses at any position Real impact: • 8 passages at single-passage latency • Better accuracy with weak retrievers • Handles unlimited conversation history • No model architecture changes needed This changes RAG economics: More context + Lower latency. (Link to the Meta paper in comments) ♻️ Repost to save someone $$$ and a lot of confusion. ✔️ You can follow @techNmak, for more insights.

100+ AI Tools to replace your tedious work: 1. Research - ChatGPT - YouChat - Abacus - Perplexity - Copilot - Gemini 2. Image - Higgsfield AI Soul - GPT-4o - Midjourney - Grok 3. Productivity - Gamma - Grok 3 - Perplexity AI - Gemini 2.5 Flash 4. Writing - Jasper - Jenny AI - Textblaze - Quillbot 5. Video - Klap - Kling - InVideo - HeyGen - Runway 6. Meeting - Tldv - Otter - Noty AI - Fireflies 7. SEO - VidIQ - Seona AI - BlogSEO - Keywrds ai - Outrank AI 8. Presentation - Decktopus - Slides AI - Gamma AI - Designs AI - Beautiful AI 9. Design - Canva - Flair AI - Designify - Clipdrop - Autodraw - Magician design 10. Audio - Lovo ai - Eleven labs - Songburst AI - Adobe Podcast 11. Marketing - Pencil - Ai-Ads - AdCopy - Simplified - AdCreative 12. Startup - Tome - Ideas AI - Namelix - Pitchgrade - Validator AI 13. Social media management - Tapilo - Typefully - Hypefury - TweetHunter