rightlane

I'm all in on this idea. Every piece of agentic coding I have done in the last month has been via an intermediate representation. Iteration is done in the IR layer mainly. It's remarkable how close you can get to a deterministic coding output using this methodology.

We are introducing new and exciting ways to expose environment variables and PII every day! Introducing features like this while we are in the midst of uncontrolled supply chain attacks feels like a not great idea.

I spend my entire day watching Claude do stuff and watching Mario Maker endless Super Expert videos on my phone. So, I thought, why not combine my love of waiting and extremely low resolution videos?!

Uses yt-dlp then extracts it to text encoding. Don't come in to this expecting something great or beautiful, but I had fun. The gif is genuine, captured in remotion from the ffmpeg -> chafa.

Your mileage may vary since there is a Claude Code bug around raw bytes per line. If they fix that, then higher resolution videos inside Claude Code is on the table. (I'm sure that will be top priority for Anthropic)

They are transparent about when it happens but no reason why. To be fair, it doesn't interrupt the flow, just drops to Opus and proceeds. The most frustrating thing is that it happened on a plan and Fable just refused to have anything to do with the plan.

My experiences so far have not been positive. The cyber security nerf is ridiculous. I am working on an AI based decompiler, every single interaction with Fable on my project has been flagged for cyber security.

Do they expect us to use this as a toy? Releasing a new more powerful model but not allowing normal use cases because the word "secure" showed up is a Dilbert comic, not a viable product.

WWDC makes me sad. It was such a great in person conference, I remember having a really weird issue with cookie handoff in Safari, and being able to sit down with a bunch of the Safari engineers to troubleshoot the issue. It started with one, then more and more engineers came to give ideas!

I appreciate making it available to everyone but it feels like there needs to be some kind of middle ground. IOS development just isn't as much fun absent the in-person community.

I disagree with every part of this.

Local LLMs are great and very useful but if you are claiming that their code quality is in the same ballpark as Claude Code or Codex with their best models I cannot consider you a serious person. I feel like this is analogous to the folks arguing that The Cloud is "someone else's computer." As if billions of dollars of spend gives these companies zero benefit over a Mac mini.

Regarding offshore, at least in my experience, better coding agent output is down to two factors. First, is subject matter expertise. Providing the right context to the coding agent based on the tech you are building for is beyond critical. That's the issue with the Vibe Coded slop projects. No expertise in a technology means no awareness of gotchas, React is the most obvious because the LLM default is to useEffect endlessly.

The bigger issue is that by their very nature LLMs are very sensitive to quality prompting in English. I have seen offshore devs fail endlessly because they don't have the English skills to successfully prompt the machine. That has caused more work for my US based devs to either carefully tune the work ticket so it is basically a coding agent prompt. Or to go through multi day exercises to enforce better prompting.

A single US dev with Claude Code is orders of magnitude better than typical offshore. Adding local models into the mix would make offshore completely useless. I'm sure many companies will see ballooning AI bills and expensive onshore devs and be very tempted to go to TCS or similar. I hope so, because that will give startups plenty of easy targets to disrupt.

Lol! Fair enough!

This is a pet project of mine that has taken on a life of its own in my head. It's still too early for me to tell if this is a good or terrible idea.

The idea is to have AI translate intent directly to LLVM IR and skip programming languages entirely.

I've gone through a few iterations starting with simple numerical operations, then I went a little crazy with it and decided to build a (mostly) self contained web server. The project site (semcom.ai) runs on a web server built this way. LLVM IR, raw Linux syscalls, no libc, static binary, scratch Docker container. IR generated by the semcom system with some interventions from Claude Code.

The system has four parts: intent layer (structured natural language), meaning compiler (intent → IR), semantic bridge (observes running system, produces behavioral model), and alignment engine (compares intent vs. behavior, outputs semantic deltas).

Me, and Claude constructed a white paper (it's on the site) with my thoughts on what this might look like. Check it out if interested!

This honestly rubs me the wrong way. I have very close friends who mightily struggle financially but they are always just outside the threshold for assistance. Basic statistics don't capture the people who are barely making it or living on debt.

The appeal to me of UBI was always that it was highlighting that everyone needs their basic needs met. The moderately paid worker barely making rent in SF needs the money as much as anybody but would never pass a means test.

This maps perfectly with what I'm seeing in the consulting space. Clients are asking exclusively for very senior developers. The expectation is that a senior developer will use AI and replace the junior devs.

The game has become how quickly can we train someone up so that the client will accept them as a "senior"

This is the best possible response to the post!

One of the last bastions of good games journalism, and the only good mobile gaming site. Another casualty of the garbage listicles and AI generated garbage that fills up search results. I would do anything to have the old, fun, internet back. This monstrosity we have now just isn't doing it for me.

My juniors thrive in a WFH environment. This is a problem with the culture and the seniors not WFH. The promotion issue is real. But let's be honest, promotion in tech mostly happens by changing jobs. The in the office people are the ones who are really slowing down their career growth.

I used to be a libertarian on drug use. Fentanyl changed my mind. It isn't a letting people have autonomy over their bodies problem anymore. The issue now is that the drugs are so deadly, getting involved in any illegal drug is like playing Russian roulette. I don't have any answers but a hard line on dealers involved with fentanyl seems like the minimum we as a society need to do.

The Apology by Plato. Short but insightful.

Dungeon Crawler Carl by Matt Dinniman. If you like LitRPG this series is just so good.

Paul's "Works of the Law" in the Perspective of Second-Century Reception by Matthew J. Thomas. If you are a theology nerd this is just exceedingly interesting.