opencode server now can run under nodejs as we're no longer using any bun specific apis we're working on a larger refactor now of its internals as we work towards a 2.0 will have nice updates to the plugin and sdk apis

Intel is proud to join the Terafab project with @SpaceX, @xAI, and @Tesla to help refactor silicon fab technology. Our ability to design, fabricate, and package ultra-high-performance chips at scale will help accelerate Terafab’s aim to produce 1 TW/year of compute to power future advances in AI and robotics. It was fun hosting @elonmusk at Intel this past weekend!

Bitlight Labs Technical Update – February 21, 2026 We are pleased to announce significant updates to our RGB Lightning Network (RLN) infrastructure and the release of a new developer sandbox. 1. RLN Node & CLI Enhancements Repository: We have refactored payment logic to a resource-oriented architecture. Key updates include: - Expanded Payment Controls: Added specific subcommands for pay invoice, offer, refund, and keysend. - BOLT12 Support: Integrated BOLT12 capabilities along with wait and abandon payment states in the API and TypeScript SDK. - Documentation: Updated all examples and docs to reflect the new node topology. 2. New Developer Sandbox Repository: We have released a React + TypeScript web frontend for the Bitlight LN Hub to facilitate testing and development. Features include: - RPC Proxy: A backend implementation (in src/app/api) to securely proxy RPC calls and resolve cross-domain restrictions. - Dockerized Environment: Includes a pre-configured Bitcoin regtest container (bitcoind) with scripts for wallet creation and rln-ldk-node server initialization. Developers are encouraged to review the repositories and update their local environments accordingly. Make Bitcoin Smart

Microsoft just hit the brakes on AI… for its own engineers. Not because the tools were bad. Because the bill got insane. For 2 years Big Tech sold one promise: “AI will replace expensive humans.” Now the companies actually using AI at scale are discovering something awkward: the AI is becoming the expensive employee. Microsoft reportedly rolled out Claude Code internally and usage exploded. Engineers used it for reviews, debugging, refactors, everything. Then finance looked at the token spend. Suddenly the same company that poured billions into Anthropic started pushing engineers off Claude and onto cheaper internal models. That alone should tell you something. Uber saw the same thing. Their engineers adopted AI fast. Leadership even gamified usage with internal rankings. But heavy users were reportedly burning thousands of dollars a month in tokens. The more productive people became with AI… the larger the infrastructure bill got. And then Nvidia’s own VP said the quiet part out loud: for some teams, compute costs are already higher than employee costs. Read that again. The chips are now costing more than the engineers. This completely breaks the story Wall Street has been pricing in: → fewer workers → lower costs → infinite productivity → bigger margins Because AI doesn’t behave like normal software. The deeper companies integrate it, the more tokens they consume. More agents → more inference More automation → more compute More usage → larger recurring bills Cheap tokens don’t automatically mean cheap systems when usage grows exponentially. That’s why companies are suddenly building internal dashboards to track AI consumption like cloud spend. The new corporate fear isn’t employees wasting time. It’s employees generating too many tokens. AI may still transform software forever. But the economics are starting to look less like “replace labor” and more like: replace payroll with an even bigger infrastructure invoice. And that changes everything.

Grok Build is amazing. The early beta just dropped for SuperGrok Heavy users and the first real feedback from developers is overwhelmingly positive. People are saying it already feels 10x ahead of other coding agents. It handles full agentic workflows natively, runs multiple agents in parallel, does live refactoring, and has a surprisingly polished terminal UI with both vim mode and mouse support. It’s fast, manages huge context cleanly, and actually feels like you’re working with a real autonomous coding partner instead of just getting suggestions. This is the kind of serious high quality tool xAI keeps shipping. If the beta keeps this momentum, Grok Build is going to be a real great tool for power users. Try it out right now at if you have SuperGrok Heavy subscription.

Grok Computer just released and it comes with full filesystem + CLI access This is the upgrade everyone’s been waiting for Regular Grok chat gives you suggestions. Grok Computer actually does the work It can now: • Directly read, edit, create, and organize files • Run any shell commands, install packages, and execute scripts • Refactor entire codebases across dozens of files in one go • Debug crashes by searching logs and fixing root causes live • Build apps, scrapers, automation scripts - then test and iterate until they work • Create images, diagrams, concept art, and memes with Grok Imagine.....saving them straight to your filesystem instantly No more copy-paste hell. No more switching tabs or describing what you want. Grok becomes a true pair programmer + creative partner that touches your actual project and generates visuals seamlessly A lot more coming soon 🚀

Why is the creator of OpenCode pretty skeptical about AI productivity gains, and the hype around AI? A very conversation @thdxr (and lots of truth bombs:) Timestamps: 00:00 Intro 07:03 Dax’s path into tech 09:04 Early startup experience 13:16 Getting involved with open source 16:13 OpenCode 23:17 Anthropic banning OpenCode 30:34 From terminal to GUI 32:34 OpenCode’s business model 36:33 Why inference is profitable 39:11 GPU bottlenecks 40:54 AI hype 45:50 AI spending 48:47 Dax’s memo 55:41 Dax’s skepticism of predictions 58:58 Engineering culture at OpenCode 1:02:38 How building works at OpenCode 1:05:36 Taste and quality 1:11:32 Dax’s work setup 1:12:35 The role of engineers and EMs 1:15:50 Advice for engineers 1:18:12 Book recommendation Brought to you by: • @AntithesisHQ – verify your system’s correctness without human review or traditional integration tests – and avoid bugs or outages • @WorkOS – everything you need to make your app enterprise ready • @turbopuffer – a vector and full-text search engine built on object storage. It’s fast, cheap, and extremely scalable Three interesting thoughts from Dax: 1. No AI-native coding agent company is “winning” by being better with AI. Dax says that none of OpenCode’s competitors are crushing them, and that nobody is using AI so well that others cannot compete. 2. Most software engineers profit from AI as time gained, not increased output — unless you change incentives! Dax says the natural way for software engineers to “cash out” their AI tooling gains is with time savings, by doing the same work as before, but faster. Until compensation and motivation structures change, most teams should expect output to stay flat while engineers go home earlier. There’s nothing wrong with this, but AI vendors sell a different outcome to CFOs: increased output. 3. AI code generation mutes the “guilt” of doing the wrong thing, but this builds up tech debt. Pre-AI, writing a hack felt bad, the second time it felt really bad, and by the third time you’d often just refactor in order to fix up the code. Now, the agent hides the hack, which skews devs’ judgment and results in less tech debt being cleaned up.

anybody who uses or learns agentic systems, SHOULD READ THIS the install order I run before any new agentic project: 1. PRIVACY: direnv + a real secrets manager install direnv, then plug it into your team's password manager (1Password CLI via op run, doppler, infisical, vault, pick one) what direnv does: loads per-folder environment variables when you cd in, unloads when you cd out. the real move is wiring it into your secrets manager so credentials NEVER live in plain text on disk what this stops: - API keys accidentally committed to git history, the most common AI agent breach pattern in 2026 - credentials leaking from one project into another through your shell history - shared .env files that one teammate quietly backs up to Dropbox - secrets that survive a laptop theft because they were sitting in /Users/you/projects the part nobody mentions: most "my agent got jailbroken" stories actually trace back to one credential the agent had access to that it shouldn't have. scope keys to projects, scope projects to folders, and the blast radius of any single compromise drops dramatically I shipped 2 agents with keys in .env files before switching. the day I plugged direnv into op run I stopped having that whole class of nightmare 2. TOKENS: litellm or portkey as your model proxy one URL that fronts every AI provider (Anthropic, OpenAI, Google, Mistral, local models). all your spend flows through one place what it saves you: - response caching keyed by prompt hash, cuts your bill 30-60% on repeat tasks - automatic fallback on rate limits (Sonnet hits a 429? falls to Opus, then GPT, then your local backup, no broken users) - per-feature and per-user budget caps, block the call before it costs $200 instead of auditing it after - model routing rules, cheap tasks to Haiku, expensive ones to Opus, never the wrong way - PII redaction before requests leave your network, security side benefit the part nobody mentions: every "$4k AI bill" story I've heard ends with "we didn't have a proxy in front." this is where you put guardrails around spend BEFORE the spend happens I built my own router for 2 weeks. it took 20 minutes to replace with litellm. I will be embarrassed about this forever 3. CONTEXT: uv + git commit on every passing eval install uv (the new Python package manager, 10-100x faster than pip+venv, by the Astral team behind ruff). then commit every time an eval suite PASSES, with the model version and pass rate in the commit message what this preserves: - exact dependency set via uv.lock, you always know which packages your agent was using, no nasty surprises from a quiet update - exact prompt + code state, you can reproduce any past run from a single git hash - exact model version paired to exact pass rate, a paper trail when prod breaks weeks later - one-command rollback to a known-working state when a refactor goes sideways - a compliance story, every prompt version tied to a model version in your commit log the security side: when something blows up in prod, you want to say "the prompt was version X, model was Sonnet 4.6.1, last eval pass rate was 94%." not "I think we deployed on Tuesday?" the first is an incident report. the second is a resignation letter I've lost more agents to "I changed 3 prompts in one session and broke something" than to any actual bug 4. VISIBILITY: mitmproxy in front of every LLM call it's basically a wiretap for your agent. install it, point your agent through it, and now you see every conversation your agent has with the model in real time what actually shows up: - every silent retry your SDK sneaks in when a call fails - the full prompt being sent (including any creds you accidentally embedded) - what the model returns BEFORE your code reacts to it - exact token cost per call, per tool, per loop iteration - responses that quietly trigger your code into doing something you didn't intend, this is where prompt injection lives the part nobody talks about: if a website your agent scraped slipped instructions into its data, mitmproxy is how you SEE the moment your agent decides to follow them. without this layer, you're trusting your agent did the right thing, not verifying I shipped 3 agents before adding this. I have no honest idea what they were doing in production 5. EVALS: inspect-ai (the framework the labs actually use) an eval framework is what tells you "this agent works" with numbers instead of vibes. inspect-ai is the one Anthropic, DeepMind, and the UK AI Safety Institute use for the eval reports you read in their papers. open source, MIT licensed what your homegrown version won't have: - run the same task across 5 different models and compare scores side by side - pre-built tests for risky agent behavior (lying, manipulating, misusing tools) - proper structure for evaluating tool-using agents, not just chat - repeatable scoring, the same input always gets graded the same way - reproducible eval seeds, so a flaky test is actually flaky and not just unlucky I wrote my own eval harness 4 times across 4 projects. threw it out 4 times if you ever want to say "my agent passes safety checks" out loud, the check has to come from a framework someone else can re-run. this is that framework the move that ties this together: keep a /lessons.md in every repo. every weird agent behavior, every edge case, every config change you find at 2am, write it down you will not remember it. you'll come back in 3 weeks and the lessons file is the only reason you still know what's going on lock these 5, keep the lessons file, your next agentic system takes 2 days instead of 2 months p.s. half of "AI agent" content online is people who've never run mitmproxy on their own loop. they don't actually know what their agent is doing. they're shipping demo videos. don't be that guy

As AI agents accelerate coding, what is the future of software engineering? Some trends are clear, such as the Product Management Bottleneck, referring to the idea that we are more constrained by deciding what to build rather than the actual building. But many implications, like AI’s impact on the job market, how software teams will be organized, and more, are still being sorted out. The theme of our AI Developer Conference on April 28-29 in San Francisco is The Future of Software Engineering. I look forward to speaking about this topic there, hearing from other speakers on this theme, and chatting with attendees about it. We’re shaping the future, and I hope you will join me there! It is currently trendy in some technology and policy circles to forecast massive job losses due to AI. Even if they have not yet materialized, these losses certainly must be just over the horizon! I have a contrarian view that the AI jobpocalypse — the notion that AI will lead to massive unemployment, perhaps even rioting in the streets — won’t be nearly as bad as dire forecasts by pundits, especially pundits who are trying to paint a picture of how powerful their AI technology is. Among professions, AI is accelerating software engineering most, given the rise of coding agents. According to a new report by Citadel Research, software engineering job postings are rising rapidly. So if software engineering is a harbinger of the impact AI will have on other professions, this expansion of software engineering jobs is encouraging. Yes, fresh college graduates are having a hard time finding jobs. And yes, there have been layoffs that CEOs have attributed to AI, even if a large fraction of this was “AI washing,” where businesses choose to attribute layoffs to AI, even though AI has not changed their internal operations much yet. And yes, there is a subset of job roles, such as call center operator, that are more heavily impacted. Many people are feeling significant job insecurity, and I feel for everyone struggling with employment, whether or not the cause is AI-related. And many other factors, such as over-hiring during the pandemic and high interest rates, have contributed to the slowdown in the labor market, and the notion that AI is leading to unemployment is oversimplified. In software engineering, I see a lot of exciting work ahead to adapt our workflows. It is already clear that: (i) As AI makes coding easier, a lot more people will be doing it. (ii) Writing code by hand and even reading (generated) code is not that important, because we can ask an LLM about the code and operate at a higher level than the raw syntax (although how high we can or should go is rapidly changing). (iii) There will be a lot more custom applications, because now it’s economical to write software for smaller and smaller audiences. (iv) Deciding what to build, more than the actual building, is becoming a bottleneck. (v) The cost of paying down technical debt is decreasing (since AI can refactor for you). At the same time, there are also a lot of open questions for our profession, such as: - In the future, what will be the key skills of a senior software engineer? And for junior levels, what should be the new Computer Science curriculum? - If everyone can build features, what skills, strategies, or resources create competitive advantage for individuals and for businesses? - What are the new building blocks (libraries, SDKs, etc.) of software? How do we organize coding agents to create software? - What should a software team look like? For example, how many engineers, product managers, designers, and so on. What tooling do we need to manage their workflow? - How do AI agents change the workflow of machine learning engineers and data scientists? For example, how can we use agents to accelerate exploring data, identifying hypotheses, and testing them? I’m excited to explore these and other questions about the future of software engineering at AI Dev. I expect this to be an exciting event. Please join us! [Original text: The Batch newsletter.]