Related posts
Stefan Zweifel GitHub
git-auto-commit-action-demo-app — A demo application to test git-auto-commit Github Action
The the words it uses that this site has seen least often elsewhere. Posts are matched on those words alone — nothing here is a summary of this one.
Top people
Showing Profile →
Hiding
Hiding
20 September
- ReleaseBrainy v8.0.0 — Brainy is a SaaS second-brain application built with .NET 10, Blazor, MudBlazor, Entity Framework Core, and SQL Server. It is inspired by Tiago Forte's PARA method and CODE workflow,…
Release notes
- Passwordify — Privacy-first password tools for the browser, and a developer API for everything else.
19 September
18 September
17 September
16 September
15 September
14 September
12 September
11 September
-
Their words
Artificial intelligence has unleashed a torrent of cheating on campus and created chaos in the job application process, as both students and employers use large language models: the former, to write hundreds of AI-assisted applications; the latter, to screen those AI-written applications with AI-written filters, thus removing from the process of finding a first job those procedural frictions sometimes known as "people."
10 September
9 September
8 September
6 September
5 September
4 September
-
Their words
It is in practice safe to assume your agents are not going to get prompt injected, even if you are kind of asking for it.
Claude Fable 5.1 and Mythos 5.1: The System Cardthezvi.substack.com
-
Their words
One thing that's under appreciated on the website of the demos is the Stanford demo where Ben showed uh anywhere between 3 to 25 images you can reconstruct that entire Stanford quad. But the thing is we had to show it from aerial view. But every single input image is been standing on the ground taking a picture from the ground. So, everything you see are generated but according to the laws of reconstruction.
3 September
2 September
1 September
31 August
30 August
-
Their words
While Western export bans have severed Russia from much of the auto market, they have not tempered the demand for brand-name SUVs and trucks. That has given rise to a sophisticated network of criminals that steals cars, hides them in shipping containers and sends them to Russia, often by way of the Middle East
28 August
27 August
26 August
From one piece DHH: Future of Programming, AI, Agentic Engineering, Vibe Coding & Linux | Lex Fridman Podcast #501 2 beliefs, in the piece's order there
-
Their words
It is an infuriatingly locked-down computer. Now, to Apple's credit, it's a pretty good computer for being locked down, but I don't want a locked-down computer. I wanna own my computer. Better yet, I wanna mutate my computer, and this is where the agentic age needs a new operating system. When you can vibe code whatever app comes to your mind, you should be able to vibe code your operating system.
-
Their words
And maybe you won't get to 100% coverage, but this is the old joke about Microsoft Office. "I only use 5%." Yeah, well, we all use a different 5%. Well, what if we all just build our own 5%? What if I just took the functionality that I need and just did that? That is a completely different challenge and one agents are incredibly capable of doing right now, today, and I've done it a lot of times over.
20 August
14 August
-
Their words
and I like the idea that since it was a process it looked kind of active and um and then it could be paired with a document that resembled it so our system was kind of a verb and a noun
13 August
12 August
-
Their words
Auto instrumentation has gotten so good in recent years. If you're using Open Telemetry and everyone should be using Open Telemetry. All of the common patterns like all of the models are trained on them. So, it is literally faster and easier to build with instrumentation than to than not to.
11 August
10 August
-
Their words
Coding isn't yet another application domain -- it's the meta-skill required for AI to automatically develop its own training material, via symbolic world models. That's how the RSI loop actually kicks off.
9 August
8 August
-
Their words
I REALLY want to believe that this fixes prompt injection risks for coding agents, but I'm just not there yet
7 August
-
On changing their mind
In the era of base LLM scaling (2022-2024), I believed the LLM line of research would reach a capability plateau (as later seen with base LLMs). In late 2024, after the o3 test-time compute demo, I changed my views: the new models were showing genuine fluid intelligence, and with this new line of work, the LLM line of research could achieve unbounded capability scaling. "There will be no wall."
5 August
3 August
From one piece Waymo Co-CEO Dmitri Dolgov: The Demo Is Only 1% Of The Work 4 beliefs, in the piece's order there
-
Their words
If you can't quantitatively define what good enough means, you're not really building a product, you're just iterating on your demo.
-
korrents.com
A working demo is at best one per cent of the work; the nines that follow it are where the real work is.Their words
And a working demo is 1% at best of the work that you have to do. The many nines of performance, the many nines of reliability that follow, that's where the real work happens.
-
Their words
And that's why every hype cycle produces a wave of absolutely spectacular demos and very few real products. And the recurring mistake of every cycle is spending on the demo when you should be saving for the nines.
+ 1 more
-
korrents.com
Waymo's demo took eighteen months and the product took fifteen years — the gap between the two is the whole job.Their words
It took us about 10 more years to begin providing a service, and then 5 more years to scale to half a million trips per week. So, the demo took 18 months, the product took about 15 years.
31 July
28 July
27 July
-
Their words
it's it's literally we're looking at neurons in the model's brain that light up when prompt injection happens. So the model won't even tell you but we can actually see those neurons and we can figure out and diagnose that it's happening. And then you combine that with the auto mode classifier and with these three layers we just cannot demonstrate prompt injection anymore.
8 July
22 June
15 June
-
Likedrcmnd.app
Laravel IdeaTheir words
Since I mostly work on Laravel projects or packages, I usually enable the Laravel Idea plugin. It's a paid plugin, but it's definitely worth the money since it can provide stuff like auto-completions for route names, request fields and more.
12 June
8 June
25 May
-
Their words
Considering every lab wants to "eat the world" the focus on how to work in real-world messy situations seems apt as their primary home.
20 May
-
Their words
So usually it will never show up in say a backend server. You would have zero uses of unsafe there. Generally when unsafe is used, it's to add a new feature to the language.
12 May
5 May
28 April
22 April
-
Their words
And so those are those places where I feel like knowing a bit about the the internals is actually like a superpower.
21 April
17 April
13 April
22 March
20 March
-
Their words
And I've gotten to a certain point and I thought it was like fairly well tuned and then I let auto research go for like overnight and it came back with like tunings that I didn't see.
11 March
27 February
20 February
31 January
-
Mixed onrcmnd.app
SuperhumanTheir words
I can say without a doubt that Superhuman is the best tool I’ve ever used to work through email quickly. There’s no single reason. The keyboard shortcuts are lightning fast. The composition tools avoid friction. Its auto-sorting is excellent. I’m just scratching the surface of the full feature set. But Superhuman comes with a significant cost at $30 a month.
20 January
16 January
10 December 2025
12 November 2025
-
korrents.com
Applications will not be wrappers around a model; the model gets wrapped into the application.Their words
we will build our own applications scaffolding which will be model forward right it won't be a wrapper on a model but the model will be wrapped into uh the application
31 October 2025
-
Their words
I think for a full GTA game, we always decided it was that there was so much Americana inherent in the IP, it would be really hard to make it work in London or anywhere else.
29 October 2025
17 October 2025
-
Their words
I think basically what takes the long amount of time and the way to think about it is that it's a march of nines and every single nine is a constant amount of work.
13 October 2025
10 October 2025
26 September 2025
11 September 2025
18 August 2025
From one piece How is AI Different Than Other Technology Waves? (With Bret Taylor and Clay Bavor) [ACQ2] 2 beliefs, in the piece's order there
-
Their words
This kind of zone of the barely doable, it's super important that to the largest extent possible, you be able to kind of control your own technology destiny.
-
Their words
many of the breakthroughs that we've had that have enabled us to to deliver such quality and cost savings and more have come through novel agent architectures and and really going down a click or two in in the stack to innovate at at lower levels of the technology stack.
14 August 2025
5 August 2025
3 August 2025
-
korrents.com
Monitoring tools that do periodic work can themselves cause the latency outliers they were installed to diagnose.Their words
One performance anti-pattern is when a company, to debug one performance problem, installs a monitoring tool that periodically does work and causes application latency outliers.
30 April 2025
-
Their words
You can't calculate every photon in the scene. You need really detailed approximations, and that's the field of computer graphics. It's about increasingly effective approximations of the laws of physics, which are just totally intractable.
28 April 2025
30 January 2025
-
Usesrcmnd.app
CursorTheir words
It is a fork of Visual Studio Code with AI-based auto completion and code generation built-in. It’s my go-to for programming with AI assistance at the moment.
16 January 2025
-
korrents.com
Building a working AI demo is far easier than turning it into a reliable production product.Their words
This is perhaps one of the first painful lessons anyone who has built an AI product quickly learns. It's easy to build a demo, but hard to build a product.
8 January 2025
10 December 2024
10 August 2024
18 June 2024
2 June 2024
18 May 2024
14 May 2024
8 May 2024
31 March 2024
-
Usesrcmnd.app
TodoistTheir words
My daily todo application is Todoist. I use Notion as a work journal to keep track of the progress of every-day tasks.
29 February 2024
19 August 2023
7 April 2023
4 July 2022
14 March 2022
22 November 2021
-
Likedaffiliate linkrcmnd.app
ShapeTheir words
Jordan Ellenberg, Shape – A really fun, witty exploration of ideas in geometry and their surprisingly wide-ranging application.
19 November 2021
21 August 2021
10 April 2021
1 June 2020
-
Recommendsaffiliate linkrcmnd.app
Fourier Analysis: An IntroductionTheir words
Not only is this a wonderful foundation for Fourier analysis, with a surprising and satisfying application to prime numbers given in the last chapter, but it's also a good starting point for analysis as a whole. Stein and Shakarchi have a series of four excellent books on the foundations of analysis, based on a now-famous series of lectures given at Princeton.
20 August 2019
-
Likedrcmnd.app
SizzyTheir words
Sizzy is a cool browser specifically for responsive design. It lets you view all of the breakpoints for a site at the same time and also does a good job auto-scaling fixed size viewports to fit whatever window size you're using.
17 July 2019
-
Usesrcmnd.app
UlauncherTheir words
I use Ulauncher as the application launcher of my preferred choice on Linux.
1 July 2019
From one piece Fast Software, the Best Software 2 beliefs · craigmod.com
-
Their words
Speed and reliability are often intuited hand-in-hand. Speed can be a good proxy for general engineering quality. If an application slows down on simple tasks, then it can mean the engineers aren’t obsessive detail sticklers.
-
Their words
Speed in software is probably the most valuable, least valued asset. To me, speedy software is the difference between an application smoothly integrating into your life, and one called upon with great reluctance.
3 April 2018
-
Usesrcmnd.app
FannyTheir words
Fanny (macOS Specific) is a free Notification Center Widget and Menu Bar application to monitor your Macs fans. Allows me to know the speed of my fans and heat generated by the CPU, so that I can make sure I keep my apps to a minimum and get the maximum performance.
12 December 2015
-
Their words
as an application developer, writing to files safely is hard enough that it should be done via some kind of library and/or database, not by directly making syscalls
13 July 2015
-
Their words
The fundamental idea I want to discuss is the definition of an application’s UI as a pure function of application state.
3 June 2015
-
korrents.com
Build a new application as a monolith first, even when you are confident it will eventually need microservices.Their words
This leads to a powerful argument for a monolith-first strategy, where you should build a new application as a monolith initially, even if you think it's likely that it will benefit from a microservices architecture later on.
20 December 2014
Nothing matches.
What is a korrent?
A korrent is a belief a person has stated in their own words: one sentence stating the claim, backed by a quote and a source, kept at korrents.com.
Under a name here, the quoted block is what they actually said. The korrent beneath it is the claim those words support, in korrents' wording — tap it to see the record, its source, and who else holds it.
Nobody here wrote their own korrents. They are compiled from public statements, and a person can change their mind, which is recorded too.
About the English under a post
Some people here publish in a language other than English. Where they do, this site shows a machine translation beneath the post, in this typeface — the site's own, not theirs.
The post itself is never changed, moved or hidden: what is set in the serif above is exactly what the person published, and it is what to quote them on. A translation can be wrong in ways that matter, especially about tone.
Only the post's own words are translated. A quoted post, a linked article and a belief on korrents.com are left in their original language.