-
Their words
NEON has nothing like it; on x64, the closest thing is the SSE4.2 string-comparison instructions (pcmpistrm), which are slow.
Related posts
Chip Huyen GitHub
metaflow-transformers-tutorials — Metaflow tutorials for ODSC West 2021
tutorialstransformersinstructions
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
18 September
17 September
16 September
8 September
-
korrents.com
Marco Rubio is struggling to hire talented staff and is settling for loyalists who follow his instructions instead.Their words
This suggests that Rubio is having some difficulties hiring anyone with talent and is settling for a putz who will do what Rubio tells him to do on Latin America.
The Devolution of the Policy Planning Staffdanieldrezner.substack.com
4 September
3 September
31 August
-
korrents.com
Human initiative to experiment without waiting for instructions is increasingly important for getting value from AI.Their words
Human agency, the willingness to push, experiment and act without waiting for instructions, seems increasingly important to getting value out of AI
26 August
-
Their words
it was actually being damaged by overly prescriptive humans. And any programmer who's had a pointy-haired boss knows exactly what that is like. When the boss walks into the room, doesn't know anything, starts telling you how to program, how to code. What do you do? You sulk. You write shittier code if you're mandated to do things that are against your better judgment. Why would an agent not be the same?
21 August
-
Their words
As the context grows, a model starts paying less attention to instructions in the middle of the context in favor of what is at the beginning and the end.
My agent.md to improve LLM-assisted code qualityfabiensanglard.net
17 August
11 August
27 July
From one piece Boris Cherny: We Cut 80% of Claude Code's Prompt 3 beliefs, in the piece's order there
-
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
the model does not seem to be prompt injectable anymore.
-
Their words
for people that aren't building agentic products, but you're using Claude code, every 6 months delete your Claude MD. Delete your skills. Delete your hooks.
17 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.
15 June
-
korrents.com
Giving LLMs explicit instructions, rather than assuming alignment, prevents emergent problems in multi-model systems.Their words
the best way with LLMs usually is to be explicit, since otherwise even if they're aligned they cause emergent problems.
2 June
-
Their words
So often with new software paradigms, what looks like inevitability turns out to be just design failure that can be solved with the right guardrails or affordances or system instructions.
25 May
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
So, I think the most important thing is sandboxing. You want your coding agent running in an environment where if something goes completely wrong, if somebody gets malicious instructions to it, that the damage is greatly limited.
-
Their words
Problem is, you can solve SQL injection by parameterizing your queries. You can't do that with LLMs.
16 February
12 February
-
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.
4 February
-
korrents.com
Programming is essentially the craft of turning ambiguous ideas into precise, specific instructions.Their words
It's not trivial to one shot something unique, because programming is the art of making the ambiguous incredibly specific through sculpting.
1 February
18 September 2025
-
Their words
I write much better emails since I became a good context engineer. I just like I now realize how much is unsaid in instructions. Why is so many things so much of what people describe in companies as politics is actually bad context engineering.
7 March 2025
-
Their words
Vibe coding can execute instructions, but deciding what the software should do and why is not automated. Product managers and designers must still do user research, market analysis, and creative brainstorming. In that sense, vibe coding changes the implementation phase more than the planning phase of the product lifecycle.
19 June 2024
-
Their words
So most people, when they advertise new context window increase, they talk a lot about finding the needle in the haystack sort of evaluation metrics and less about whether there’s any degradation in the instruction following performance. So I think that’s where you need to make sure that throwing more information at a model doesn’t actually make it more confused.
16 January 2024
-
Their words
I suspect that in the future, it'll be easier to get models to output exactly what we need with minimal prompting, and these techniques will become less important.
10 January 2024
-
korrents.com
Advice on how hard to work should only be taken from someone who has burned out before.Their words
My rule is never to take instructions on how hard I should work from someone who hasn’t burned out before.
21 September 2023
-
korrents.com
The collapse postulate cannot simply be discarded without replacement instructions for measurements.Their words
As we just saw, one cannot just discard the Collapse Postulate. For this reason, if one does calculations in any Many Worlds approach, one must effectively replace the Collapse Postulate by other assumptions, notably about what happens to observers and/or measurement devices when worlds branch.
15 September 2023
-
Recommendsrcmnd.app
ChatGPT Custom InstructionsTheir words
Using Custom Instructions properly can completely transform your experience with ChatGPT.
25 May 2022
-
Their words
Pure discovery learning, where students are never shown instructions or examples, fails miserably.
6 April 2022
4 March 2022
-
korrents.com
The next-token language modeling objective is misaligned with following user instructions helpfully and safely.Their words
This is because the language modeling objective used for many recent large LMs-predicting the next token on a webpage from the internet-is different from the objective "follow the user's instructions helpfully and safely" (Radford et al.,, 2019; Brown et al.,, 2020; Fedus et al.,, 2021; Rae et al.,, 2021; Thoppilan et al.,, 2022). Thus, we say that the language modeling objective is misaligned.
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.