Related posts
Sunil Pai Blog
The subject this post names, from the same vocabulary the directory files beliefs under, and the word 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
19 September
17 September
14 September
13 September
12 September
10 September
9 September
8 September
7 September
-
Their words
Yea video game gfx pipelines will now just visually prompt neural renderers.
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
3 September
-
korrents.com
Large layoffs tend to push out the best employees, who quit for competitors or start their own companies.Their words
That’s the problem with large layoffs; they prompt precisely the best employees to quit to join competitors, or launch their own businesses.
2 September
-
Their words
I don’t trust Claude to summarize its own system prompts when there’s a risk that material from its system prompt might impact its opinions.
19 August
-
Their words
The first thing I do is I try to make sure that if there is a summary at the very end, here are all the decisions that were made, I will read through that end to end. If there hasn't been, I will prompt for that decision process.
14 August
10 August
From one piece Peter Steinberger: "Fun Is Velocity" 2 beliefs, in the piece's order there
-
korrents.com
Pick something hard and boring: fun problems are the crowded ones now that anybody can prompt a thing into existence.Their words
Maybe I would pick something again that's that's in the category hard and boring because that's usually a category that is a little bit easier to actually find people that will appreciate when you solved something. If you pick something that is fun, even if it's hard, you're gonna have a very tough time, especially in a time where people can just prompt things into existence.
-
Their words
You know features are the fun part. A new feature is is just a prompt away. The real cost comes after every feature we shipped of course with a configuration option because we didn't want to break everyone's setup.
9 August
-
Their words
“you are a devil’s advocate, disagree with everything” is probably the worst possible prompt for this agent. within a week everyone would ignore her. she’d become the slack equivalent of a smoke detector that goes off whenever somebody makes toast.
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
2 August
-
korrents.com
Interviews reward presentation; only a hands-on case study shows how fast a candidate's thinking decays.Their words
the number of people who present incredibly well, and then you give them a prompt and some data and ask them to come back with a PRD on something, and then we make them verbally defend it, how quickly the thinking decays from folks who are good at the theater, but not the specifics, uh is kind of really telling, I think.
27 July
From one piece Boris Cherny: We Cut 80% of Claude Code's Prompt 5 beliefs, in the piece's order there
-
Their words
And what's interesting is that the model is actually a little bit more intelligent without these prompts.
-
Their words
And you don't want to guess what's the instruction that the model needs because you might not predict it correctly. The thing that you want to do is you want to run it.
-
Their words
I think the skill nowadays is less about prompt engineering and more about figuring out how do you give Claude a hard task that seems a little bit too hard. And then how do you make it possible for Claude to verify its work along the way? And the verification I think is probably the single most important thing that people do not get right
+ 2 more
-
Their words
the model does not seem to be prompt injectable anymore.
-
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.
19 July
15 July
-
Their words
But it's also your instruction budget is like if you give the model too many instructions and especially too many conflicting instructions and that's in your initial prompt and also like if you have a conversation you start going down a path and then you change your mind and you start going down a different you actually I don't want to do any of that I want to do this. It's like a it's a lot of computation the model has to do to notice that it has to ignore that whole thing.
13 July
30 June
-
Usesrcmnd.app
XcodeTheir words
When writing code, I'm mostly in Xcode, often in concert with Prompt and, lately, Claude Code.
-
Usesrcmnd.app
Claude CodeTheir words
When writing code, I'm mostly in Xcode, often in concert with Prompt and, lately, Claude Code.
2 June
27 April
20 March
-
Their words
So the question is how do I refactor all the abstractions so that I'm not I have to arrange it once and hit go. The name of the game is how can you get more agents running for longer periods of time without your involvement doing stuff on your behalf?
19 March
From one piece Simon Willison: Engineering practices that make coding agents work - The Pragmatic Summit 2 beliefs, in the piece's order there
-
Their words
I call it the lethal trifecta because the only guaranteed solution is to cut off one of the legs.
-
Their words
Problem is, you can solve SQL injection by parameterizing your queries. You can't do that with LLMs.
20 February
12 February
From one piece OpenClaw: The Viral AI Agent that Broke the Internet - Peter Steinberger | Lex Fridman Podcast #491 3 beliefs, in the piece's order there
-
Their words
So, so the latest generation of models has a lot of post-training to detect those approaches, and it's not as simple as ignore all previous instructions and do this and this. That was years ago. You have to work much harder to do that now. Still possible.
-
korrents.com
The chat box is not the final form of working with models; it is radio shows recorded onto television.Their words
Like, if you think more globally, we are, we copied Google for agents. You have, like, a prompt, and, and then you have a chat interface. That, to me, very much feels like when we first created television and then people recorded radio shows on television and you saw that on TV.
-
korrents.com
Do not run a personal agent on a cheap or local model: weak models are gullible and easy to prompt-inject.Their words
That's why I warn in my security documentation, don't use cheap models. Don't use Haiku or a local model. Even though I, I very much love the idea that this thing could completely run local. If you use a, a very weak local model, they are very gullible. It's very easy to, to prompt inject them.
15 January
21 September 2025
-
korrents.com
If you cannot say crisply what success looks like, you will not get great work — out of a team or out of an AI.Their words
if you're really unclear about what success looks like the prompt, you're probably not going to get the most amazing work. Um I think that's true for managing teams and it's very much true for managing AIs.
2 September 2025
-
Their words
Like it seems to me right now you could do like a double blind test of the same prompt given to Grock Claude Gemini um Mistral Deep Seek. Do a double blind test. I bet most people wouldn't be able to tell which is which.
25 August 2025
-
Mixed onrcmnd.app
GPT-5Their words
GPT-5 also is much more literal in how you have to prompt it - it’s a great model but not the best agent, you have to be more precise and specific.
19 August 2025
9 August 2025
-
Their words
One of my favorite papers about prompt injection is Design Patterns for Securing LLM Agents against Prompt Injections
3 August 2025
25 May 2025
-
Lovedrcmnd.app
Anthropic prompt engineering documentationTheir words
I still think Anthropic have the best prompting documentation of any LLM provider.
6 May 2025
-
Their words
Unless you’re an extreme power user, asking AI questions every day is still a rounding error on your total electricity footprint.
What's the carbon footprint of using ChatGPT?hannahritchie.substack.com
22 March 2025
-
korrents.com
Prompt injection is an extremely hard attack to defend against, and hardly anyone integrating AI is talking about it.Their words
One thing that I don't think a lot of people are talking about as we integrate more and more AI is that prompt injection is an extremely hard thing to defend against because it's not really clear how you defend against it.
30 January 2025
-
Likedrcmnd.app
llmTheir words
This is a command line tool with plenty of plugins that lets you prompt different models. Think of it as a command-line version of Open WebUI. It’s particularly useful for quick scripting and basic automation.
31 December 2024
-
Their words
There’s still plenty to worry about with respect to the environmental impact of the great AI datacenter buildout, but a lot of the concerns over the energy cost of individual prompts are no longer credible.
29 September 2024
-
Dislikedrcmnd.app
iTermTheir words
iTerm: Tmux is slow, prompt layout breaks when resizing the window.
31 August 2024
-
korrents.com
Art is what results from making an enormous number of choices, and a prompt contains almost none of them.Their words
But let me offer a generalization: art is something that results from making a lot of choices.
19 June 2024
-
Their words
And also this is where I believe the whole prompt engineering, trying to be a good prompt engineer is not going to be a long-term thing. I think you want to make products work where a user doesn’t even ask for something, but you know that they want it and you give it to them without them even asking for it.
24 January 2024
24 October 2023
26 June 2023
-
korrents.com
Half the population in rich countries is not articulate enough in writing to use prompt-driven AI well.Their words
For sure, half the population is insufficiently articulate in writing to use ChatGPT well.
22 June 2023
-
Their words
I doubt that the current set of generative AI tools, like ChatGPT, Bard, etc., are representative of the UIs we’ll be using in a few years because they have deep-rooted usability problems.
AI Is First New UI Paradigm in 60 Yearsjakobnielsenphd.substack.com
15 March 2023
15 December 2022
22 December 2020
-
Likedrcmnd.app
Windows TerminalTheir words
Windows Terminal - Finally Windows has a modern terminal. You can run shells like Command Prompt, PowerShell, and Windows Subsystem for Linux (WSL).
22 February 2018
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.