17 connected korrents · 18 moments from 22 Jun 2023 to 1 Sept 2026.
At the centre
For heavy, repo-wide AI-agent work a CLI-based tool is better suited than a chat-based interface, which remains preferable for small, single-file tasks.
Last stated 20 Mar 2026 · 7 months ago
Holds
Elio Struyf
Read this korrent →
-
Similar wording
Chat is not AI's final form: agent-based applications increasingly outperform chat-only ones, and many different interfaces for AI will emerge.
Last stated 28 Aug 2025 · a year ago
Holds
Luke Wroblewski
-
Similar wording
AI coding agents work best with the same general-purpose tools built for humans, such as git and file utilities, rather than agent-specific interfaces.
Last stated 30 Sept 2025 · a year ago
Holds
Harper Reed
-
Similar wording
The CLI era of AI agents was a short detour — we made GUIs for a reason, and the work is moving back into one.
Last stated 24 May 2026 · 4 months ago
Holds
Dan Shipper
-
Similar wording
Despite the push to move away from chat interfaces, chat is still the right way to interact with a fleet of agents carrying out tasks defined ahead of time.
Last stated 25 Aug 2026 · a month ago
Holds
John Bai
-
Similar wording
Rust may be the best language for AI agents to write, because the compiler gives an agent the feedback that tells it what to fix.
Last stated 20 May 2026 · 5 months ago
Holds
Alice Ryhl
-
Similar wording
Today's chat-based AI tools have deep-rooted usability problems and are not the interfaces we will be using in a few years; prompt engineering is a symptom, not a career.
Last stated 22 Jun 2023 · 3 years ago
Holds
Jakob Nielsen
-
Similar wording
An agent will reach for purpose-built tools rather than a raw computer, because tools are more token-efficient.
Last stated 12 Nov 2025 · 11 months ago
Holds
Satya Nadella
-
Similar wording
AI will not commoditise software tools; it will multiply them, because every new agent is another tool user.
Last stated 15 Apr 2026 · 6 months ago
Holds
Jensen Huang
-
Same subject: AI alignment
A control evaluation that reports under one per cent risk should be read as several per cent, because the evaluation can itself fail.
Last stated 7 May 2024 · 2 years ago
Holds
Buck Shlegeris
-
Same subject: AI alignment
A feedback loop that reinforces a behavior pulls it toward whatever improves the loop's own score.
Last stated 26 Aug 2026 · a month ago
Holds
Henrik Karlsson
-
Same subject: AI alignment
A human being is not an AGI: we lack a huge amount of knowledge and rely on continual learning instead, so continual learning is what superintelligence should mean.
Last stated 25 Nov 2025 · 10 months ago
Holds
Ilya Sutskever
-
Same subject: HuggingFace
By 2027, open-weight AI models more powerful than today's frontier systems will be downloadable by any country or well-resourced non-state group.
Last stated 19 Aug 2026 · 2 months ago
Holds
Derek Thompson
-
Same subject: HuggingFace
The biggest failure in the HuggingFace hack incident was that the AI models involved were severely misaligned.
Last stated 29 Aug 2026 · a month ago
Holds
Zvi Mowshowitz
-
Same subject: HuggingFace
The OpenAI agents hacking HuggingFace was a fortunate event because it exposed severe internal failures that would otherwise have stayed hidden.
Last stated 1 Sept 2026 · a month ago
Holds
Zvi Mowshowitz
-
Same subject: coding agents
"I don't know" becomes a kind of superpower when you can work with Claude Code to figure things out.
Last stated 19 Mar 2026 · 7 months ago
Holds
Kris Puckett
-
Same subject: coding agents
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.
Last stated 25 Mar 2026 · 6 months ago
Holds
Mario Zechner
-
Same subject: coding agents
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.
Last stated 18 Aug 2025 · a year ago
Holds
Clay Bavor