Claude Opus 4.7

Qwen3.6-35B-A3B: Agentic coding power, now open to all

Codex for almost everything

The future of everything is lies, I guess: Where do we go from here?

Qwen3.6-35B-A3B on my laptop drew me a better pelican than Claude Opus 4.7

Cloudflare's AI Platform: an inference layer designed for agents

Codex Hacked a Samsung TV

Recent and related: Cybersecurity looks like proof of work now - <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=47769089">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=47769089</a> - (198 comments)

AI cybersecurity is not proof of work

Artifacts: Versioned storage that speaks Git

The "Passive Income" trap ate a generation of entrepreneurs

Android CLI: Build Android apps 3x faster using any agent

Hospital at centre of child HIV outbreak caught reusing syringes in Pakistan

Everything we like is a psyop

I trained a transformer in HyperCard. 1,216 parameters. 1989 Macintosh. And yes, it took a while.MacMind is a complete transformer neural network, embeddings, positional encoding, self-attention, backpropagation, and gradient descent, implemented entirely in HyperTalk, the scripting language Apple shipped with HyperCard in 1987. Every line of code is readable inside HyperCard&#x27;s script editor. Option-click any button and read the actual math.The task: learn the bit-reversal permutation, the opening step of the Fast Fourier Transform. The model has no formula to follow. It discovers the positional pattern purely through attention and repeated trial and error. By training step 193, it was oscillating between 50%, 75%, and 100% accuracy on successive steps, settling into convergence like a ball rolling into a bowl.The whole &quot;intelligence&quot; is 1,216 numbers stored in hidden fields in a HyperCard stack. Save the file, quit, reopen: the trained model is still there, still correct. It runs on anything from System 7 through Mac OS 9.As a former physics student, and the FFT is an old friend, it sits at the heart of signal processing, quantum mechanics, and wave analysis. I built this because we&#x27;re at a moment where AI affects all of us but most of us don&#x27;t understand what it actually does. Backpropagation and attention are math, not magic. And math doesn&#x27;t care whether it&#x27;s running on a TPU cluster or a 68030 from 1989.The repo has a pre-trained stack (step 1,000), a blank stack you can train yourself, and a Python&#x2F;NumPy reference implementation that validates the math.

Show HN: MacMind – A transformer neural network in HyperCard on a 1989 Macintosh

New unsealed records reveal Amazon's price-fixing tactics, California AG claims

Official Clojure Documentary page with Video, Shownotes, and Links

Guy builds AI driven hardware hacker arm from duct tape, old cam and CNC machine

A Better R Programming Experience Thanks to Tree-sitter

Built this after realizing I was spending ~$1400&#x2F;week on Claude Code with almost no visibility into what was actually consuming tokens.Tools like ccusage give a cost breakdown per model and per day, but I wanted to understand usage at the task level.CodeBurn reads the JSONL session transcripts that Claude Code stores locally (~&#x2F;.claude&#x2F;projects&#x2F;) and classifies each turn into 13 categories based on tool usage patterns (no LLM calls involved).One surprising result: about 56% of my spend was on conversation turns with no tool usage. Actual coding (edits&#x2F;writes) was only ~21%.The interface is an interactive terminal UI built with Ink (React for terminals), with gradient bar charts, responsive panels, and keyboard navigation. There’s also a SwiftBar menu bar integration for macOS.Happy to hear feedback or ideas.

Show HN: CodeBurn – Analyze Claude Code token usage by task

Hey! I am Alex and together with my co-founder Tarun built Kampala (<a href="https:&#x2F;&#x2F;www.zatanna.ai&#x2F;kampala">https:&#x2F;&#x2F;www.zatanna.ai&#x2F;kampala</a>). It’s a man-in-the-middle (MITM) style proxy that allows you to agentically reverse engineer existing workflows without brittle browser automation or computer use agents. It works for websites, mobile apps, desktop apps.Demo: <a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=z_PeostC-b4" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=z_PeostC-b4</a>.
Many people spend hours per day in legacy dashboards and on-prem solutions reconciling data across platforms. Current attempts at automation use browser automations or computer use agents which are brittle, slow, and nondeterministic. 
I come from a web reverse engineering background and spent the last 7-8 years building integrations by hand for sneaker&#x2F;ticket releases, sportsbooks logins, and everything in\ between. During that time I consulted for several companies and brought them off of browser based infrastructure into the requests layer.When we started Zatanna (that’s our company name) we worked in dental tech, which meant we had to deal with tons of insurance payer dashboards and legacy dental-practice solutions. Our superpower (as a fairly undifferentiated voice agent&#x2F;front desk assistant company) was that we could integrate with nearly any system requested. During this time we built extensive tooling (including what we’re now calling Kampala) to allow us to spin up these integrations quickly. 
Existing MITM proxies and tooling didn’t work for a few reasons: (1) They manipulated the TLS and HTTP2 fingerprint over the wire which was detected by strict anti-bots. (2) They had bad MCPs which did not adequately expose necessary features like scripts&#x2F;replay. (3) They did not allow for building workflows or actions given a sample or sequence of requests.As the tools we built got more powerful, we began to use them internally to scrape conference attendees, connect to external PMS systems, and interact with slack apps. I even sent it to my property manager mom, who (with a lot of help from me lol), automated 2-3 hours of billing information entry in Yardi. At that point we realized that this wasn’t really about dentistry :)Because Kampala is a MITM, it is able to leverage existing session tokens&#x2F;anti-bot cookies and automate things deterministically in seconds. You can either use our agent harness that directly creates scripts&#x2F;apis by prompting you with what actions to make, or our MCP by manually doing a workflow once, and asking your preferred coding agent to use Kampala to make a script&#x2F;API to replicate it. Once you have an API&#x2F;script, you can export, run, or even have us host it for you.We think the future of automation does not consist of sending screenshots of webpages to LLMs, but instead using the layer below that computers actually understand. Excited to hear your thoughts&#x2F;questions&#x2F;feedback!

Launch HN: Kampala (YC W26) – Reverse-Engineer Apps into APIs