Slouching Towards Bethlehem – Joan Didion (1967)

Three types of LLM workloads and how to serve them

Evolution Unleashed (2018)

Scientists find a way to regrow cartilage in mice and human tissue samples

200 MB RAM FreeBSD desktop

Speech: <a href="https:&#x2F;&#x2F;ec.europa.eu&#x2F;commission&#x2F;presscorner&#x2F;detail&#x2F;da&#x2F;speech_26_150" rel="nofollow">https:&#x2F;&#x2F;ec.europa.eu&#x2F;commission&#x2F;presscorner&#x2F;detail&#x2F;da&#x2F;speech...</a>

EU–INC – A new pan-European legal entity

I built this as a small side project to learn and experiment, and I ended up with this!I used a subdomain from my personal portfolio, and everything else runs on free tiers.The project uses Nuxt, SVG, Cloudflare Workers, D1 (SQL), KV, Terraform, and some agentic coding with OpenAI Codex and Claude Code.What started as a joke among friends turned into a fun excuse to build something end to end, from zero to production, and to explore a few things 
I’d never touched before.I’d really appreciate any feedback or suggestions.

Show HN: Open-source certificate from GitHub activity

I'll pass on your zoom call

Spotify won court order against Anna's Archive, taking down .org domain

Batmobile: 10-20x Faster CUDA Kernels for Equivariant Graph Neural Networks

Open source server code for the BitCraft MMORPG

Hey HN! I built Retain as the evolution of claude-reflect (github.com&#x2F;BayramAnnakov&#x2F;claude-reflect).The original problem: I use Claude Code&#x2F;Codex daily for coding, plus claude.ai and ChatGPT occasionally. Every conversation contains decisions, corrections, and patterns I forget existed weeks later. I kept re-explaining the same preferences.claude-reflect was a CLI tool that extracted learnings from Claude Code sessions. Retain takes this further with a native macOS app that:- Aggregates conversations from Claude Code, claude.ai, ChatGPT, and Codex CLI
- Instant full-text search across thousands of conversations (SQLite + FTS5)It&#x27;s local-first - all data stays in a local SQLite database. No servers, no telemetry. Web sync uses your browser cookies to fetch conversations directly.

Show HN: Retain – A unified knowledge base for all your AI coding conversations

Hi HN, we&#x27;re Sam, Shane, and Abhi.Almost a year ago, we first shared Mastra here (<a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=43103073">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=43103073</a>). It’s kind of fun looking back since we were only a few months into building at the time. The HN community gave a lot of enthusiasm and some helpful feedback.Today, we released Mastra 1.0 in stable, so we wanted to come back and talk about what’s changed.If you’re new to Mastra, it&#x27;s an open-source TypeScript agent framework that also lets you create multi-agent workflows, run evals, inspect in a local studio, and emit observability.Since our last post, Mastra has grown to over 300k weekly npm downloads and 19.4k GitHub stars. It’s now Apache 2.0 licensed and runs in prod at companies like Replit, PayPal, and Sanity.Agent development is changing quickly, so we’ve added a lot since February:- Native model routing: You can access 600+ models from 40+ providers by specifying a model string (e.g., `openai&#x2F;gpt-5.2-codex`) with TS autocomplete and fallbacks.- Guardrails: Low-latency input and output processors for prompt injection detection, PII redaction, and content moderation. The tricky thing here was the low-latency part.- Scorers: An async eval primitive for grading agent outputs. Users were asking how they should do evals. We wanted to make it easy to attach to Mastra agents, runnable in Mastra studio, and save results in Mastra storage.- Plus a few other features like AI tracing (per-call costing for Langfuse, Braintrust, etc), memory processors, a `.network()` method that turns any agent into a routing agent, and server adapters to integrate Mastra within an existing Express&#x2F;Hono server.(That last one took a bit of time, we went down the ESM&#x2F;CJS bundling rabbithole, ran into lots of monorepo issues, and ultimately opted for a more explicit approach.)Anyway, we&#x27;d love for you to try Mastra out and let us know what you think. You can get started with `npm create mastra@latest`.We&#x27;ll be around and happy to answer any questions!

Show HN: Mastra 1.0, open-source JavaScript agent framework from the Gatsby devs

A common approach to automating Amazon shopping or similar complex websites is to reach for large cloud models (often vision-capable). I wanted to test a contradiction: can a ~3B parameter local LLM model complete the flow using only structural page data (DOM) plus deterministic assertions?This post summarizes four runs of the same task (search → first product → add to cart → checkout on Amazon). The key comparison is Demo 0 (cloud baseline) vs Demo 3 (local autonomy); Demos 1–2 are intermediate controls.More technical detail (architecture, code excerpts, additional log snippets):<a href="https:&#x2F;&#x2F;www.sentienceapi.com&#x2F;blog&#x2F;verification-layer-amazon-case-study" rel="nofollow">https:&#x2F;&#x2F;www.sentienceapi.com&#x2F;blog&#x2F;verification-layer-amazon-...</a>Demo 0 vs Demo 3:Demo 0 (cloud, GLM‑4.6 + structured snapshots)
 success: 1&#x2F;1 run
 tokens: 19,956 (~43% reduction vs ~35k estimate)
 time: ~60,000ms
 cost: cloud API (varies)
 vision: not requiredDemo 3 (local, DeepSeek R1 planner + Qwen ~3B executor)
 success: 7&#x2F;7 steps (re-run)
 tokens: 11,114
 time: 405,740ms
 cost: $0.00 incremental (local inference)
 vision: not requiredLatency note: the local stack is slower end-to-end here largely because inference runs on local hardware (Mac Studio with M4); the cloud baseline benefits from hosted inference, but has per-token API cost.ArchitectureThis worked because we changed the control plane and added a verification loop.1) Constrain what the model sees (DOM pruning).
We don’t feed the entire DOM or screenshots. We collect raw elements, then run a WASM pass to produce a compact “semantic snapshot” (roles&#x2F;text&#x2F;geometry) and prune the rest (often on the order of ~95% of nodes).2) Split reasoning from acting (planner vs executor).Planner (reasoning): DeepSeek R1 (local) generates step intent + what must be true afterward.
Executor (action): Qwen ~3B (local) selects concrete DOM actions like CLICK(id) &#x2F; TYPE(text).
3) Gate every step with Jest‑style verification.
After each action, we assert state changes (URL changed, element exists&#x2F;doesn’t exist, modal&#x2F;drawer appeared). If a required assertion fails, the step fails with artifacts and bounded retries.Minimal shape:ok = await runtime.check(
 exists(&quot;role=textbox&quot;),
 label=&quot;search_box_visible&quot;,
 required=True,
).eventually(timeout_s=10.0, poll_s=0.25, max_snapshot_attempts=3)What changed between “agents that look smart” and agents that work
Two examples from the logs:Deterministic override to enforce “first result” intent: “Executor decision … [override] first_product_link -&gt; CLICK(1022)”Drawer handling that verifies and forces the correct branch: “result: PASS | add_to_cart_verified_after_drawer”The important point is that these are not post‑hoc analytics. They are inline gates: the system either proves it made progress or it stops and recovers.Takeaway
If you’re trying to make browser agents reliable, the highest‑leverage move isn’t a bigger model. It’s constraining the state space and making success&#x2F;failure explicit with per-step assertions.Reliability in agents comes from verification (assertions on structured snapshots), not just scaling model size.

A verification layer for browser agents: Amazon case study

RTS for Agents

App Subscription is now my Weekend Project

GenAI, the snake eating its own tail

IPv6 is not insecure because it lacks a NAT

Prediction markets are ushering in a world in which news becomes about gambling

Mystery of the Head Activator

Hi HN,I built this because I often work in coworking spaces or do screen sharing, and I&#x27;ve always had this fear of accidentally flashing my .env file with production secrets to the whole room (or recording).It’s a simple VS Code extension that opens .env files in a custom grid editor. It automatically masks any value longer than 6 characters so I can safely open the file to check keys without exposing the actual secrets.It runs 100% locally with zero dependencies (I know how sensitive these files are). It just reads the file, renders the grid, and saves it back as standard text.It&#x27;s open source (MIT) and I&#x27;d love any feedback on the masking logic or other features that would make it safer to use.Marketplace: <a href="https:&#x2F;&#x2F;marketplace.visualstudio.com&#x2F;items?itemName=xinbenlv.dotenv-mask-editor" rel="nofollow">https:&#x2F;&#x2F;marketplace.visualstudio.com&#x2F;items?itemName=xinbenlv...</a> Github <a href="https:&#x2F;&#x2F;github.com&#x2F;xinbenlv&#x2F;dotenv-mask-editor" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;xinbenlv&#x2F;dotenv-mask-editor</a>

Show HN: Dotenv Mask Editor: No more embarrassing screen leaks of your .env

I finally got my sway layout to autostart the way I like it

Internet voting is insecure and should not be used in public elections

Instabridge has acquired Nova Launcher

SmartOS

Seeing a lot of people running coding agents (Claude Code, etc.) in custom sandboxes Docker&#x2F;VMs, firejail&#x2F;bubblewrap, scripts that gate file or network access.Curious to know what&#x27;s missing that makes people DIY this? And what would a &quot;good enough&quot; standard look like?

Ask HN: Why are so many rolling out their own AI/LLM agent sandboxing solution?

Hey folks, I’m Hassan, one of the co-founders of Infracost (<a href="https:&#x2F;&#x2F;www.infracost.io">https:&#x2F;&#x2F;www.infracost.io</a>). Infracost helps engineers see and reduce the cloud cost of each infrastructure change before they merge their code.
The way Infracost works is we gather pricing data from Amazon Web Services, Microsoft Azure and Google Cloud. What we call a ‘Pricing Service’, which now holds around 9 million live price points (!!). Then we map these prices to infrastructure code. Once the mapping is done, it enables us to show the cost impact of a code change before it is merged, directly in GitHub, GitLab etc. Kind of like a checkout-screen for cloud infrastructure.We’ve been building since 2020 (we were part of YC W21 batch), and iterating on the product, building out a team etc. However, back in 2020 one of our users asked if we can also show the carbon impact alongside costs.It has been itching my brain since then. The biggest challenge has always been the carbon data. The mapping of carbon data to infrastructure is time consuming, but it is possible since we’ve done it with cloud costs. But we need the raw carbon data first. The discussions that have happened in the last few years finally led me to a company called Greenpixie in the UK. A few of our existing customers were using them already, so I immediately connected with the founder, John.Greenpixie said they have the data (AHA!!) And their data is verified (ISO-14064 &amp; aligned with the Greenhouse Gas Protocol). As soon as I talked to a few of their customers, I asked my team to see if we can actually finally do this, and build it.My thinking is this: some engineers will care, and some will not (or maybe some will love it and some will hate it!). For those who care, cost and carbon are actually linked; meaning if you reduce the carbon, you usually reduce the cost of the cloud too. It can act as another motivation factor.And now, it is here, and I’d love your feedback. Try it out by going to <a href="https:&#x2F;&#x2F;dashboard.infracost.io&#x2F;">https:&#x2F;&#x2F;dashboard.infracost.io&#x2F;</a>, create an account, set up with the GitHub app or GitLab app, and send a pull request with Terraform changes (you can use our example terraform file). It will then show you the cost impact alongside the carbon impact, and how you can optimize it.I’d especially love to hear your feedback on if you think carbon is a big driver for engineers within your teams, or if carbon is a big driver for your company (i.e. is there anything top-down about carbon).AMA - I’ll be monitoring the thread :)Thanks

Show HN: See the carbon impact of your cloud as you code

The Unix Pipe Card Game

I&#x27;ve been trying to get agentic coding to work, but the dissonance between what I&#x27;m seeing online and what I&#x27;m able to achieve is doing my head in.Is there real evidence, beyond hype, that agentic coding produces net-positive results? If any of you have actually got it to work, could you share (in detail) how you did it?By &quot;getting it to work&quot; I mean:
 * creating more value than technical debt, and
 * producing code that’s structurally sound enough for someone responsible for the architecture to sign off on.Lately I’ve seen a push toward minimal or nonexistent code review, with the claim that we should move from “validating architecture” to “validating behavior.” In practice, this seems to mean: don’t look at the code; if tests and CI pass, ship it. I can’t see how this holds up long-term. My expectation is that you end up with &quot;spaghetti&quot; code that works on the happy path but accumulates subtle, hard-to-debug failures over time.When I tried using Codex on my existing codebases, with or without guardrails, half of my time went into fixing the subtle mistakes it made or the duplication it introduced.Last weekend I tried building an iOS app for pet feeding reminders from scratch. I instructed Codex to research and propose an architectural blueprint for SwiftUI first. Then, I worked with it to write a spec describing what should be implemented and how.The first implementation pass was surprisingly good, although it had a number of bugs. Things went downhill fast, however. I spent the rest of my weekend getting Codex to make things work, fix bugs without introducing new ones, and research best practices instead of making stuff up. Although I made it record new guidelines and guardrails as I found them, things didn&#x27;t improve. In the end I just gave up.I personally can&#x27;t accept shipping unreviewed code. It feels wrong. The product has to work, but the code must also be high-quality.

Top Stories