Tap a claim on the ring to put it at the centre.
← Large language models are too chaotic and language too ambiguous for…
17 connected korrents · 19 moments from 11 Oct 2018 to 14 Sept 2026. Nearly all of them are about compilers .
Everything filed under LLMs
LLMs
Everything filed under developer tools
developer tools
Everything filed under benchmarks
benchmarks
Everything filed under coding agents
coding agents
Everything filed under AI agents
AI agents Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Read this korrent: Large language models are too chaotic and language too ambiguous for them to preserve the reasoning guarantees that compilers provide. Large language models are too chaotic and language too ambiguous for them to preserve the reasoning guarantees that compilers provide. Last stated 6 months ago
14 Apr 2026
KK
Kyle Kingsbury — holds since 2026-04-14 — tap for who they are
Same subject: A compiler that also serves an IDE has to be lazy and deferred throughout — a different way of building compilers from the one the textbooks teach. — tap to centre the map on it A compiler that also serves an IDE has to be lazy and deferred throughout — a different way of building compilers from the one the textbooks teach. Last stated 5 months ago
13 May 2026
AH
Anders Hejlsberg — holds since 2026-05-13 — tap for who they are
Same subject: A compiler that names every place a change breaks turns refactoring into fixing errors until the compiler stops shouting. — tap to centre the map on it A compiler that names every place a change breaks turns refactoring into fixing errors until the compiler stops shouting. Last stated 4 months ago
20 May 2026
AR
Alice Ryhl — holds since 2026-05-20 — tap for who they are
Same subject: A programming language is not a compiler but an experience: editing, running, debugging and the runtime library all have to fit together as one cycle. — tap to centre the map on it A programming language is not a compiler but an experience: editing, running, debugging and the runtime library all have to fit together as one cycle. Last stated 5 months ago
13 May 2026
AH
Anders Hejlsberg — holds since 2026-05-13 — tap for who they are
Same subject: A speed difference between languages that share the LLVM backend measures the benchmark author, not the languages. — tap to centre the map on it A speed difference between languages that share the LLVM backend measures the benchmark author, not the languages. Last stated 2 years ago
22 Mar 2025
TH
ThePrimeagen — holds since 2025-03-22 — tap for who they are
Same subject: Agents are the new compilers that compile intent into fast software. — tap to centre the map on it Agents are the new compilers that compile intent into fast software. Last stated 3 weeks ago
12 Sept 2026
GR
Guillermo Rauch — holds since 2026-09-12 — tap for who they are
Same subject: AI agents are only as good as the proof-checkers, compilers, type systems, and linters given to them. — tap to centre the map on it AI agents are only as good as the proof-checkers, compilers, type systems, and linters given to them. Last stated 3 weeks ago
14 Sept 2026
GR
Guillermo Rauch — holds since 2026-09-14 — tap for who they are
Same subject: As AI takes over more of the coding process, clearly specifying goals and exercising good judgment will matter more than ever. — tap to centre the map on it As AI takes over more of the coding process, clearly specifying goals and exercising good judgment will matter more than ever. Last stated 8 months ago
4 Feb 2026
SH
Scott Hanselman — holds since 2026-02-04 — tap for who they are
Same subject: Assembly is far simpler to learn than the modern web stack: anyone who can vertically centre a div can learn to read it. — tap to centre the map on it Assembly is far simpler to learn than the modern web stack: anyone who can vertically centre a div can learn to read it. Last stated a month ago
26 Aug 2026
CM
Casey Muratori — holds since 2026-08-26 — tap for who they are
Same subject: A badly written AI outbound email is evidence of a bad vendor, not of a limit of AI. — tap to centre the map on it A badly written AI outbound email is evidence of a bad vendor, not of a limit of AI. Last stated 9 months ago
1 Jan 2026
JL
Jason Lemkin — holds since 2026-01-01 — tap for who they are
Same subject: A bigger context window does not give you a smarter model; the intelligence of the model is what decides how much of that window it can actually attend to. — tap to centre the map on it A bigger context window does not give you a smarter model; the intelligence of the model is what decides how much of that window it can actually attend to. Last stated 3 months ago
15 Jul 2026
DH
Dex Horthy — holds since 2026-07-15 — tap for who they are
Same subject: A child who has seen ten cats learns what a machine needs the whole internet of cat photos for, by a learning pathway nobody has solved. — tap to centre the map on it A child who has seen ten cats learns what a machine needs the whole internet of cat photos for, by a learning pathway nobody has solved. Last stated 2 months ago
10 Aug 2026
FL
Fei-Fei Li — holds since 2026-08-10 — tap for who they are
Same subject: AI progress is faster than people expect, and ordinary scaling can be enough to solve problems that looked very hard. — tap to centre the map on it AI progress is faster than people expect, and ordinary scaling can be enough to solve problems that looked very hard. Last stated 2 years ago
2 Feb 2025
AC
Ajeya Cotra — holds since 2023-08-29 — tap for who they are
SA
Scott Alexander — holds since 2022-09-12 — tap for who they are
MB
Miles Brundage — holds since 2025-02-02 — tap for who they are
Same subject: As models keep growing, AI is running out of enough high-quality unique training tokens to keep up. — tap to centre the map on it As models keep growing, AI is running out of enough high-quality unique training tokens to keep up. Last stated 3 months ago
24 Jun 2026
LW
Lilian Weng — holds since 2026-06-24 — tap for who they are
Same subject: Current techniques restrict pre-trained representation power because standard language models are unidirectional. — tap to centre the map on it Current techniques restrict pre-trained representation power because standard language models are unidirectional. Last stated 8 years ago
11 Oct 2018
KT
Kristina Toutanova — holds since 2018-10-11 — tap for who they are
MC
Ming-Wei Chang — holds since 2018-10-11 — tap for who they are
KL
Kenton Lee — holds since 2018-10-11 — tap for who they are
JD
Jacob Devlin — holds since 2018-10-11 — tap for who they are
Same subject: A tiny language model inventing a plausible-sounding name is the same phenomenon as a large one confidently stating a false fact. — tap to centre the map on it A tiny language model inventing a plausible-sounding name is the same phenomenon as a large one confidently stating a false fact. Last stated 8 months ago
12 Feb 2026
AK
Andrej Karpathy — holds since 2026-02-12 — tap for who they are
Same subject: AI labs are extremely dependent on chain-of-thought monitoring, which may not last much longer as models edge into steganographic obfuscation. — tap to centre the map on it AI labs are extremely dependent on chain-of-thought monitoring, which may not last much longer as models edge into steganographic obfuscation. Last stated 3 weeks ago
10 Sept 2026
ZM
Zvi Mowshowitz — holds since 2026-09-10 — tap for who they are
Same subject: AI should be released iteratively rather than built in secret, because AI and surprise do not go together and the world needs time to adapt before it is under the gun. — tap to centre the map on it AI should be released iteratively rather than built in secret, because AI and surprise do not go together and the world needs time to adapt before it is under the gun. Last stated 3 years ago
18 Mar 2024
SA
Sam Altman — holds since 2024-03-18 — tap for who they are
At the centre
Large language models are too chaotic and language too ambiguous for them to preserve the reasoning guarantees that compilers provide.
Holds Read this korrent →
A compiler that also serves an IDE has to be lazy and deferred throughout — a different way of building compilers from the one the textbooks teach.
Holds
A compiler that names every place a change breaks turns refactoring into fixing errors until the compiler stops shouting.
Holds
A programming language is not a compiler but an experience: editing, running, debugging and the runtime library all have to fit together as one cycle.
Holds
A speed difference between languages that share the LLVM backend measures the benchmark author, not the languages.
Holds
Agents are the new compilers that compile intent into fast software.
Holds
AI agents are only as good as the proof-checkers, compilers, type systems, and linters given to them.
Holds
As AI takes over more of the coding process, clearly specifying goals and exercising good judgment will matter more than ever.
Holds
Assembly is far simpler to learn than the modern web stack: anyone who can vertically centre a div can learn to read it.
Holds
A badly written AI outbound email is evidence of a bad vendor, not of a limit of AI.
Holds
A bigger context window does not give you a smarter model; the intelligence of the model is what decides how much of that window it can actually attend to.
Holds
A child who has seen ten cats learns what a machine needs the whole internet of cat photos for, by a learning pathway nobody has solved.
Holds
AI progress is faster than people expect, and ordinary scaling can be enough to solve problems that looked very hard.
Holds
As models keep growing, AI is running out of enough high-quality unique training tokens to keep up.
Holds
Current techniques restrict pre-trained representation power because standard language models are unidirectional.
Holds
A tiny language model inventing a plausible-sounding name is the same phenomenon as a large one confidently stating a false fact.
Holds
AI labs are extremely dependent on chain-of-thought monitoring, which may not last much longer as models edge into steganographic obfuscation.
Holds
AI should be released iteratively rather than built in secret, because AI and surprise do not go together and the world needs time to adapt before it is under the gun.
Holds