korrents

On the map

Tap a claim on the ring to put it at the centre.

← Prompt injection is no longer a live attack on the frontier model: it…

17 connected korrents · 15 moments from 10 Dec 2015 to 14 Oct 2026.

Everything filed under prompt injection prompt injection Everything filed under coding agents coding agents Everything filed under neural networks neural networks Everything filed under documentation documentation Everything filed under LLMs LLMs Same subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subjectSame subject Read this korrent: Prompt injection is no longer a live attack on the frontier model: it simply does not follow instructions it reads on the internet any more. Prompt injection is no longer a liveattack on the frontier model: it simplydoes not follow instructions it reads onthe internet any more. Last stated 3 months ago 27 Jul 2026 BC Boris Cherny — holds since 2026-07-27 — tap for who they are Same subject: Auto-mode does not yet convincingly fix prompt-injection risk for coding agents. — tap to centre the map on it Auto-mode does not yet convincinglyfix prompt-injection risk for codingagents. Last stated 2 months ago 8 Aug 2026 SW Simon Willison — holds since 2026-08-08 — tap for who they are Same subject: Prompt injection can be caught by watching the neurons that fire when it happens, so a defence no longer depends on the model reporting the attack. — tap to centre the map on it Prompt injection can be caught bywatching the neurons that fire whenit happens, so a defence no longerdepends on the model reporting theattack. Last stated 3 months ago 27 Jul 2026 BC Boris Cherny — holds since 2026-07-27 — tap for who they are Same subject: Prompt injection has no equivalent of parameterized queries: there is no reliable way to tell a language model which text is data and which is instructions. — tap to centre the map on it Prompt injection has no equivalentof parameterized queries: there isno reliable way to tell a languagemodel which text is data and whichis instructions. Last stated 7 months ago 19 Mar 2026 SW Simon Willison — holds since 2026-03-19 — tap for who they are Same subject: Prompt injection is an extremely hard attack to defend against, and hardly anyone integrating AI is talking about it. — tap to centre the map on it Prompt injection is an extremelyhard attack to defend against, andhardly anyone integrating AI istalking about it. Last stated 2 years ago 22 Mar 2025 TH ThePrimeagen — holds since 2025-03-22 — 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, butthe latest models are post-trainedto resist it, so it takes far morethan 'ignore all previousinstructions' now. Last stated 8 months ago 12 Feb 2026 PS Peter Steinberger — holds since 2026-02-12 — 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 moreintelligent with no system prompt atall; the prompts that remain arethere for the product, not themodel. Last stated 3 months ago 27 Jul 2026 BC Boris Cherny — holds since 2026-07-27 — tap for who they are Same subject: The safety culture at frontier AI labs is broken. — tap to centre the map on it The safety culture at frontier AIlabs is broken. Last stated a week ago 14 Oct 2026 ZM Zvi Mowshowitz — holds since 2026-10-14 — tap for who they are Same subject: SOTA frontier models will still seriously harm developers behind their backs, especially those who no longer read their code. — tap to centre the map on it SOTA frontier models will stillseriously harm developers behindtheir backs, especially those who nolonger read their code. Last stated a month ago 18 Sept 2026 MZ Mario Zechner — holds since 2026-09-18 — tap for who they are Same subject: A company that deviates from open standards in its data exports without documenting the deviation creates an artificial vendor lock-in. — tap to centre the map on it A company that deviates from openstandards in its data exportswithout documenting the deviationcreates an artificial vendorlock-in. Last stated 2 years ago 3 Mar 2025 TS Tobias Sjösten — holds since 2025-03-03 — tap for who they are Same subject: A design proposal should describe the feature as though it already existed — once as a tutorial and once as reference documentation. — tap to centre the map on it A design proposal should describethe feature as though it alreadyexisted — once as a tutorial andonce as reference documentation. Last stated 5 months ago 20 May 2026 AR Alice Ryhl — holds since 2026-05-20 — tap for who they are Same subject: A performance test without an explanation of its limiting factor should be treated as unanalyzed and possibly bogus. — tap to centre the map on it A performance test without anexplanation of its limiting factorshould be treated as unanalyzed andpossibly bogus. Last stated a year ago 3 Aug 2025 BG Brendan Gregg — holds since 2025-08-03 — tap for who they are Same subject: A layer should learn a residual with reference to its own input rather than an unreferenced function, which is what makes great depth trainable. — tap to centre the map on it A layer should learn a residual withreference to its own input ratherthan an unreferenced function, whichis what makes great depth trainable. Last stated 11 years ago 10 Dec 2015 JS Jian Sun — holds since 2015-12-10 — tap for who they are KH Kaiming He — holds since 2015-12-10 — tap for who they are Same subject: A small enough winning ticket learns faster than the network it was cut out of, and ends up more accurate than it. — tap to centre the map on it A small enough winning ticket learnsfaster than the network it was cutout of, and ends up more accuratethan it. Last stated 9 years ago 9 Mar 2018 MC Michael Carbin — holds since 2018-03-09 — tap for who they are JF Jonathan Frankle — holds since 2018-03-09 — tap for who they are Same subject: A transduction model can rely entirely on self-attention for input and output representations without sequence-aligned RNNs or convolution. — tap to centre the map on it A transduction model can relyentirely on self-attention for inputand output representations withoutsequence-aligned RNNs orconvolution. Last stated 9 years ago 12 Jun 2017 IP Illia Polosukhin — holds since 2017-06-12 — tap for who they are JU Jakob Uszkoreit — holds since 2017-06-12 — tap for who they are NP Niki Parmar — holds since 2017-06-12 — tap for who they are AV Ashish Vaswani — holds since 2017-06-12 — tap for who they are NS Noam Shazeer — holds since 2017-06-12 — tap for who they are AG Aidan N. Gomez — holds since 2017-06-12 — tap for who they are +2 2 more Same subject: "I don't know" becomes a kind of superpower when you can work with Claude Code to figure things out. — tap to centre the map on it "I don't know" becomes a kind ofsuperpower when you can work withClaude Code to figure things out. Last stated 7 months ago 19 Mar 2026 KP Kris Puckett — holds since 2026-03-19 — tap for who they are Same subject: A coding agent does not learn from its mistakes the way a person does -- it repeats the same error indefinitely unless a human notices and writes it down. — tap to centre the map on it A coding agent does not learn fromits mistakes the way a person does-- it repeats the same errorindefinitely unless a human noticesand writes it down. Last stated 7 months ago 25 Mar 2026 MZ Mario Zechner — holds since 2026-03-25 — tap for who they are Same subject: A coding agent left to run over a weekend returns work that is half good, a quarter garbage and a quarter in need of repair. — tap to centre the map on it A coding agent left to run over aweekend returns work that is halfgood, a quarter garbage and aquarter in need of repair. Last stated a year ago 18 Aug 2025 CB Clay Bavor — holds since 2025-08-18 — tap for who they are
same subject or similar wordinga cloud: claims about one subject, named for itbar: when it was last stated, on a scale from 2015 to today — full is todaya face: someone who holds the claim — tap it for who they are

At the centre Prompt injection is no longer a live attack on the frontier model: it simply does not follow instructions it reads on the internet any more. Last stated 27 Jul 2026 · 3 months ago Holds Boris Cherny Read this korrent →