mayank
Joined 16 years ago
Karma
2,721
Submissions
595
Member since
Sep 11
Recent submissions
Comment · 2 months ago
If you’re doing breakeven math on subscriptions, consider that your own rig can run 24/7 whereas you will get a fraction of that with sub rate limits. Even if you factor in PG&E residential rates, the breakeven is a lot closer to months for overnight long-running agentic coding a couple times a week.
And in terms of interesting use cases: recently pointed an agent at Blender and gave it vision. That setup can essentially iterate on a scene forever.
Comment · 2 months ago
I assume this is a strictly B2B proposition in spite of "built for every side of the GPU market" -- meaning I'm probably not going to be able to buy/bid on small (e.g. 2-8) lots of used, matched RTX 3090s for example?
Comment · 3 months ago
Close to $500 in overage for me :) I’m going to give GLM a shot next.
Comment · 3 months ago
Oddly enough, I did the exact same thing this past weekend, for a couple hundred usd in Fable overage.
It was truly remarkably easy to build and package it exactly to my whims, in my case as a single docker container with a process reaper that runs llama, my Go code, tts, chat harness, browser in xvfb, and even a mailer daemon. With Gemma, it even runs on a RPi 5.
What’s absolutely wild to me is that over a couple hours, I could probably have it import parts of Home Assistant for my devices directly, and do other wacky stuff in what is essentially software for one.
Comment · 3 months ago
I was curious about the cost angle too, i.e. how much "free" coding agent I can get for what cost. Here's the research by Fable if you're interested: https://claude.ai/public/artifacts/2c9a5001-0b7e-4944-beb1-9...
Comment · 3 months ago
Spent nights over the last six months combining AI coding agents with containers, spec-driven development, and formal verification, so that I (eventually) don't have to manually review 10k+ lines of AI code a day, or worry about the latest model wiping out my home directory:
https://www.overplane.dev/ (Apache-2.0)
Comment · 3 months ago
TL;DR: Overplane is an AI build system that pairs popular AI coding agents with containers, spec driven development, and automatic lightweight formal verification for a safer, replayable AI codegen workflow.
Like many others, I’ve watched AI code pile up at work, and get increasingly lighter reviews due to its size and maddening uniformity. On my side projects at night, I see the full speed and fragility of vibe coding. Neither practice seems sustainable, so I’ve been playing around for the last few months looking for a balanced, middle ground.
The key idea here is similar to chip design: if AI written software functionally does what you intended it to (by virtue of increasingly sophisticated testing against a codification of your intent), then it’s perhaps less important to manually review every line of generated code.
Overplane is a labor of love that brings that idea to life as an open-source experiment, combining some old personal loves: containerization, content addressed build systems, and formal verification.
The example I’d start with is rustdis, a partial, wire-compatible Redis clone in Rust with an empty [dependencies] section. Created with seven short specs and about $45 of Claude Opus, in about three hours: https://www.overplane.dev/examples
What sold me on the approach is that the one IR generated by Overplane from the specs paid for itself downstream: Z3 checks at build time, 48 generated proptest properties, and Kani proofs on the parser and arithmetic core.
It also holds up against redis-benchmark better than I expected, within about 90% of real Redis on my box unpipelined and a bit ahead on some pipelined workloads, which I mostly attribute to rustdis doing less than Redis does.
It’s v0.0.8 and rough. If you’ve tried spec-first workflows or lightweight formal methods in anger, I’d love to hear where they broke down for you.
Comment · 4 months ago
Such a great comment, and I agree with all of them.
For me in a similar vein:
- mar ‘24: thinking about how to survey the field and implement a hard research task in Natural Language Processing, and then just approximating it well enough with a prompt and a completions api
- mid ‘25: Llama 3 being able to analyze a good sized codebase I was onboarding onto, and synthesize it into diagrams that matched the quality of ones I’d generated by hand with deterministic tools.
- dec ‘25: opus 4.5 basically generating multi-class modules and tests perfectly (syntactically). Finding that errors were my own under-specification of the prompt. Stopped writing code by hand, mainly because it was good enough and came with tests, docs, build scripts, and other goodies for free.
Comment · 1 year ago
Indeed! It’s a form of a branch table: https://en.m.wikipedia.org/wiki/Branch_table
Comment · 1 year ago
Got a source for this? Because it’s brilliant.
Comment · 1 year ago
Agreed and flagged, this almost seems LLM written, not a bit of data.
Comment · 1 year ago
This seems odd. If your scribe can lie in complex and sometimes hard to detect ways, how do you not see some form of risk? What happens when (not if) your scribe misses something and real world damages ensue as a result? Are you expecting your users to cross check every report? And if so, what’s the benefit of your product?
Comment · 2 years ago
> They need to reword this. Whoever wrote it is a liability
Sounds like it’s been written specifically to avoid liability.
https://www.linkedin.com/in/mayanklahiri/