damn... in my archives I've found a .dat file from the year 2008, no visible textual data inside... almost removed it... Codex: "this is the Miranda IM database file, 90k ICQ messages from three years"🤯🤯🤯
“properly prompted”
Replying to @Perpetualmaniac
This is no longer a real issue. C is superior again, because very complex pointer and memory management is no problem for a properly prompted AI.
TL;DR if you haven't watched it yet
The End of Programming? Video of my talk yesterday at #scaladays. youtube.com/watch?v=jlJyuJhD…
Aleksandr Shvedov retweeted
Anthropic is offering a 145k salary for a personal assistant in London.
Responsibilities include:
"Scheduling and managing calendars for leader(s) and their organization"
"Building and maintaining organizational systems for tracking and managing inbound requests"
"Managing the leader's inbox and communications with precise attention to detail"
"Handling travel logistics"
Somebody should really build some sort of tech tool that can handle this stuff autonomously.
this week in AI native software engineering: let's kill all or "intermediary" abstractions. "every layer is just one more place for the agent to guess wrong".
my new AI native software engineering principle is to delete as many layers of abstraction as possible
at this point, all my webapps are written in rust and compiled to wasm, UI is rendered directly in html and/or raw webgpu calls
no react/threejs/nextjs or any other intermediary abstractions
all my effort goes into writing custom validation harnesses for each app that fully quantifies perf / usability / what "good" means for the coding agent so it can hillclimb it
every agent sessions are planned via my explore unknowns skill (github.com/dzhng/skills), so all major decisions are frontloaded, then I just let the agent rip for 12+ hrs
at this point I'm solo shipping products that I wouldn't even dare to dream of a year ago
I think this is a great point no one is willing to accept :)
Replying to @GergelyOrosz
If AI is basic like the keyboard then let candidates use it in the interview.
You cannot require it at work and ban it in the test. So which one is the real job?
Aleksandr Shvedov retweeted
$300 for a bug that gives free access to OpenAI’s paid models with no API key or account.
Zero reason to report anything else I find to them.
AI devs are still able to surprise me with the development things they are trying to discard :) High-level languages, human code review, now… tests! Yesterday I thought it is all about verification loops…
We deleted 800k lines of unit tests from the @sazabi monorepo earlier this week.
Three hypotheses:
1- Unit tests "lock-in" slop code by making it hard to change or remove
2- Unit tests slow down dev cycles by making your agent do more work locally and by increasing CI times
3- Unit tests waste money by making your agent generate more tokens and by adding useless CI runs
Will report back soon with the results!
That’s cool! I have always dreamed for the future where the layout of the “logical”, human-written “procedures” is completely transformed at the runtime, to execute faster/have more optimal register allocations/offload the dead & cold code.
Aleksandr Shvedov retweeted
o cara que desistiu de programação em 2023
This Post is from an account that no longer exists. Learn more
Sorry, but what is the point? Hardware that no one can afford. Specs that are both overkill for the “agentic era” development and too far from user machines. Same fate as other recent dev projects like Volterra and Dev Box — irrelevance and abandonment.
Today, we introduced Project Zenith, a ready-to-code Windows experience on developer-class hardware. Alongside @jackhuynh I also shared that Project Zenith will first be available on systems powered by @AMD’s Ryzen AI Halo. With more devices from our partners coming in the months ahead. blogs.windows.com/windowsdev…























