Tap a claim on the ring to put it at the centre.
← You cannot predict which instructions a model needs, so a system…
8 connected korrents · 7 moments on record from 3 Feb 2025 to 12 Aug 2026.
Everything filed under scaling laws
scaling laws Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Read this korrent: You cannot predict which instructions a model needs, so a system prompt has to be discovered by running the thing rather than designed in advance. You cannot predict which instructions a model needs, so a system prompt has to be discovered by running the thing rather than designed in advance. Last stated a month ago
27 Jul 2026
BC
Boris Cherny — holds since 2026-07-27 — tap for who they are
Same subject: A frontier model is measurably more intelligent with no system prompt at all; the prompts that remain are there for the product, not the model. — tap to centre the map on it A frontier model is measurably more intelligent with no system prompt at all; the prompts that remain are there… Last stated a month ago
27 Jul 2026
BC
Boris Cherny — holds since 2026-07-27 — tap for who they are
Same subject: Predictions that nobody will write code soon dodge the question of what code is: prompting a model is still producing something we will have to read and change. — tap to centre the map on it Predictions that nobody will write code soon dodge the question of what code is: prompting a model is still… Last stated 5 months ago
7 Apr 2026
MF
Martin Fowler — holds since 2026-04-07 — tap for who they are
Same subject: Prompt injection is unsolved, but the latest models are post-trained to resist it, so it takes far more than 'ignore all previous instructions' now. — tap to centre the map on it Prompt injection is unsolved, but the latest models are post-trained to resist it, so it takes far more than 'ignore… Last stated 7 months ago
12 Feb 2026
PS
Peter Steinberger — holds since 2026-02-12 — tap for who they are
Same subject: Context has two budgets, not one: the information budget everyone thinks about, and an instruction budget, where conflicting instructions cost the model real computation to ignore. — tap to centre the map on it Context has two budgets, not one: the information budget everyone thinks about, and an instruction budget, where… Last stated 2 months ago
15 Jul 2026
DH
Dex Horthy — holds since 2026-07-15 — tap for who they are
Same subject: Reasoning will generalize the way instruction tuning did: add enough verifiable domains and, at some point nobody can yet locate, the rest start working on their own. — tap to centre the map on it Reasoning will generalize the way instruction tuning did: add enough verifiable domains and, at some point nobody can… Last stated 2 years ago
3 Feb 2025
NL
Nathan Lambert — holds since 2025-02-03 — tap for who they are
Same subject: A model you have to fine-tune for each thing you want it to do is not a general-purpose model. — tap to centre the map on it A model you have to fine-tune for each thing you want it to do is not a general-purpose model. Last stated 4 weeks ago
12 Aug 2026
CF
Chelsea Finn — holds since 2026-08-12 — tap for who they are
Same subject: Every machine-learning deployment that has paid off so far left a person making the decision, which is the only reason imperfect models were useful. — tap to centre the map on it Every machine-learning deployment that has paid off so far left a person making the decision, which is the… Last stated 4 weeks ago
12 Aug 2026
CF
Chelsea Finn — holds since 2026-08-12 — tap for who they are
Same subject: AI does not remove a job so much as change what it consists of, and knowing exactly where a model's capabilities stop is now part of being a good engineer. — tap to centre the map on it AI does not remove a job so much as change what it consists of, and knowing exactly where a model's… Last stated 11 months ago
16 Oct 2025
DF
Dylan Field — holds since 2025-10-16 — tap for who they are
At the centre
You cannot predict which instructions a model needs, so a system prompt has to be discovered by running the thing rather than designed in advance.
Holds Read this korrent →
A frontier model is measurably more intelligent with no system prompt at all; the prompts that remain are there for the product, not the model.
Holds
Predictions that nobody will write code soon dodge the question of what code is: prompting a model is still producing something we will have to read and change.
Holds MF Martin Fowler
Prompt injection is unsolved, but the latest models are post-trained to resist it, so it takes far more than 'ignore all previous instructions' now.
Holds
Context has two budgets, not one: the information budget everyone thinks about, and an instruction budget, where conflicting instructions cost the model real computation to ignore.
Holds DH Dex Horthy
Reasoning will generalize the way instruction tuning did: add enough verifiable domains and, at some point nobody can yet locate, the rest start working on their own.
Holds NL Nathan Lambert
A model you have to fine-tune for each thing you want it to do is not a general-purpose model.
Holds CF Chelsea Finn
Every machine-learning deployment that has paid off so far left a person making the decision, which is the only reason imperfect models were useful.
Holds CF Chelsea Finn
AI does not remove a job so much as change what it consists of, and knowing exactly where a model's capabilities stop is now part of being a good engineer.
Holds DF Dylan Field