James Yanyuk

agent runtimes ( and drones (

[Pete Hegseth @PeteHegseth]

🇺🇸

[sophie @netcapgirl]

fable 5 when you ask it for the bedtime story your grandma used to tell you about enriching uranium

[James Yanyuk @yanyuk]

@yigitkonur @superdoteng End up finding any good agentic IDE with good SSH support?

[James Yanyuk @yanyuk]

@boardyai Building persistent sandboxes for coding agents and an OSS agentic IDE for disposable cloud workspaces. Bring your own sandbox and harness!

[david friedberg @friedberg]

they’re not jobs if they’re not valued. they’re not valued if there aren’t customers out there willing to pay them for their great work. needing the government to “create” a job is tantamount to welfare and that level of welfare resolves these individuals to a dependency on the government and lack of economic mobility. and chains our people, collectively, to a more indentured future.

you may be well intentioned but you have, and always will, fail to see the destitute folly of government as a job creation engine.

i have tried to engage you on this topic, in good faith, with empiricism and reasoning, but you have only dodged my points and pivoted to some populist refrain about the importance of taxation and the evils of productivity-driven success.

i can only assume you’re dodging these truths because you and the rest of the politburo leadership have deemed the conversation unsafe speech and put your oligopoly at risk.

let’s leave it at that then.

perhaps if your ways get their day, we can all bask in the glories of the dark ages ahead.

[Elon Musk @elonmusk]

@LorenaSGonzalez Message received

[James Yanyuk @yanyuk]

@HeyGarrison Appreciate that! Expect to see Pad on the benchmarks soon :)

[James Yanyuk @yanyuk]

@gabriel1 @steipete Yeah, biggest misconception of tools like Wispr Flow is that you need to one-shot a prompt without mistakes, and then have “retakes” when a mistake comes though

[James Yanyuk @yanyuk]

@charlieholtz Can we bring our own sandbox provider?

[James Yanyuk @yanyuk]

@chr1sa The "before" photo for @paddotdev

[Aidan Mattis @MattisRedacted]

An astronaut talked about his Christian faith while rounding the moon over Easter last week.

[Andrej Karpathy @karpathy]

Judging by my tl there is a growing gap in understanding of AI capability.

The first issue I think is around recency and tier of use. I think a lot of people tried the free tier of ChatGPT somewhere last year and allowed it to inform their views on AI a little too much. This is a group of reactions laughing at various quirks of the models, hallucinations, etc. Yes I also saw the viral videos of OpenAI's Advanced Voice mode fumbling simple queries like "should I drive or walk to the carwash". The thing is that these free and old/deprecated models don't reflect the capability in the latest round of state of the art agentic models of this year, especially OpenAI Codex and Claude Code.

But that brings me to the second issue. Even if people paid $200/month to use the state of the art models, a lot of the capabilities are relatively "peaky" in highly technical areas. Typical queries around search, writing, advice, etc. are *not* the domain that has made the most noticeable and dramatic strides in capability. Partly, this is due to the technical details of reinforcement learning and its use of verifiable rewards. But partly, it's also because these use cases are not sufficiently prioritized by the companies in their hillclimbing because they don't lead to as much $$$ value. The goldmines are elsewhere, and the focus comes along.

So that brings me to the second group of people, who *both* 1) pay for and use the state of the art frontier agentic models (OpenAI Codex / Claude Code) and 2) do so professionally in technical domains like programming, math and research. This group of people is subject to the highest amount of "AI Psychosis" because the recent improvements in these domains as of this year have been nothing short of staggering. When you hand a computer terminal to one of these models, you can now watch them melt programming problems that you'd normally expect to take days/weeks of work. It's this second group of people that assigns a much greater gravity to the capabilities, their slope, and various cyber-related repercussions.

TLDR the people in these two groups are speaking past each other. It really is simultaneously the case that OpenAI's free and I think slightly orphaned (?) "Advanced Voice Mode" will fumble the dumbest questions in your Instagram's reels and *at the same time*, OpenAI's highest-tier and paid Codex model will go off for 1 hour to coherently restructure an entire code base, or find and exploit vulnerabilities in computer systems. This part really works and has made dramatic strides because 2 properties: 1) these domains offer explicit reward functions that are verifiable meaning they are easily amenable to reinforcement learning training (e.g. unit tests passed yes or no, in contrast to writing, which is much harder to explicitly judge), but also 2) they are a lot more valuable in b2b settings, meaning that the biggest fraction of the team is focused on improving them. So here we are.

[The Reverend Mister @turtology]

My sons, watching Artemis II launch from their front yard in Orlando.

[Garry Tan @garrytan]

The unit of software production has changed from team-years to founder-days.

Act accordingly.

[Steve Ruiz @steveruizok]

there was a moment in 2023 when your team was using Figma, Linear, VS Code, Typescript, React 18, esbuild or Next.js with the pages router. Peak software in every category. wonderful stack. you were young and happy and in love

[DOW Rapid Response @DOWResponse]

A prayer for our warriors🙏🏼🙏🏼🙏🏼

[Sahil Lavingia @shl]

CEOs should code

[Peter Steinberger 🦞 @steipete]

@notsunsakis @bcherny don't call it vibe coding - that's associated with yolo i smash head on keyboard, not thinking, engineering, building, testing, debugging, iterating.

agentic engineering, or just...coding. We move faster, but it's still hard.

[James Yanyuk @yanyuk]

@JC70769 @Tesla @cybertruck What's the wrap you have on it?

[Guillermo Rauch @rauchg]

Not knowing how to code giving you an advantage is absolute nonsense.

The more you understand, the better your prompts, the better the feedback you give, the better product you ship.

What will change is that the intricacies of syntax, compilers, module systems, the finer details of type systems, won’t matter as much to everyone.

But you should absolutely understand how the pieces fit together. From syscall to pixels. Learn how data flows, because you’ll be able to secure your systems. Learn about performance, because you’ll be able to push your agent further. Learn about APIs, because they determine how to integrate systems. Learn about how systems fail, because you’ll be able to make reliable programs.