Back issues
the harness and the model improved together and their curves crossed last winter; models keep absorbing the harness and what is left is a harness for human attention
Andrew Ng relaunches around AI engineering with four skills drawn from ten thousand job postings and dozens of interviews; a training-market signal about what employers name
Lovable's CTO on apps that agents can use: capabilities an agent calls instead of screens a person clicks, one entry point to all the work — the machine audience arriving as a product strategy
if code is free, why is the desktop app still built on a web wrapper: what the state of coding agents says about what actually gets rewritten
Handshake acquires Uplimit and the analyst reads it as AI skilling changing direction; a training-market signal for the commercial desk
an open model against a frontier model on a coding benchmark: the frontier model wins single-shot, the open one wins with more attempts at about sixty-four percent less per solved task, and routing between them beats either — the token-budget beat with a vendor's numbers (the platform sells the open model)
the same open model against Claude Fable 5: near-equal single-shot quality, a third the cost per solved task, the closed model more reliable four-for-four; vendor benchmark, cite with attribution
a research note modelling Anthropic's eight-times code-merge figure into a serial researcher uplift plausibly above two, stated as one analyst's opinion with others at the lab disagreeing
three hundred forty-nine technical workers asked about value gained rather than time saved, because the two differ when the tool changes which tasks you do; self-reported, dated May
tokenmaxxing is not valuemaxxing: a self-hosted agent-platform vendor on token spend, junior pull requests and what value actually is; the fetched body is the podcast footer
the harness and the model improved together and their curves crossed last winter; models keep absorbing the harness and what is left is a harness for human attention
the centre of developer work moves from the editor to supervising agents: the control plane becomes the primary surface and the editor one instrument under it, with named tools and a new interface built for it
spec-driven development a month in: a spec plus conformance tests as the whole input, and collaboration that looks like commenting on a document rather than merging code
Gradio's workflow builder makes the pipeline the interface: typed nodes on a canvas, every intermediate visible, the same graph a deploy — the inner loop drawn
ten percent worse, a hundred times cheaper: every year one more part of the pipeline flips from human-made to model-made, argued as a pattern with a first case each
agentic memory is a dose calibrated to the model: strong models take the full guideline set, weaker ones a compact core plus retrieval, saturated ones show no gain; eight models measured, one gaining sixteen points for five percent more tokens
six coding agents' system prompts clustered and swapped between agents: the model sets the ceiling, the prompt decides whether it is reached — an experiment, reproducible
context rot is a quality failure, not a capacity one, and recursive language models are one design for handling long context today; a clear explainer with sources
what AI context architecture is and why not to build your own: keeping the focused context the system needs, not everything it could see; a plain explainer
multi-vector late-interaction retrieval lands in a mainstream embedding library; a retrieval-quality tool for the context desk, technical
AI did not kill code review, it made the burden of proof explicit: a change ships with evidence it works or it is work moved downstream; solos lean on tests, teams on review for risk and intent — two figures in it unsourced
held-out sets for speech benchmarks because public leaderboards get optimised for the test; the benchmark-gaming lesson from voice, applicable to any score a vendor quotes
a five-agent software lifecycle built with a QA mindset, with two papers on cross-layer observability for LLM-assisted test automation; the fetched body is the episode's footer
an independent pre-deployment evaluation of a frontier model, run under NDA with the developer reviewing the post; what an outside check of a model release actually consists of
a pilot assessing misalignment risk from agents used inside four frontier labs, organised by means, motive and monitoring; the first cross-company exercise of its kind, dated May
OpenAI will wind down its model contract with Cursor after the SpaceX acquisition, shutoff proposed for November 12; the model behind a coding agent can be withdrawn by contract — the executive dependency beat in one announcement
every individual contributor becomes a team lead of agents, and that reshapes review, interviewing and the balance of human and agent judgment; the remaining bottleneck is getting an organisation's data into a state agents can reason over
about one in twenty engineers are explorers who push the agent further than asked and the rest want a paved path; cloning the explorers is the wrong move — one executive's estimate
the real issue under model terms-of-use fights is embedded judgment: models carry perspectives and the biggest buyers will want to audit and influence post-training — the executive dependency beat
how Amazon's frontier teams became AI native; the fetched body is the podcast footer, the claim rides on the linked write-up
OpenAI's custom inference chip at Hot Chips: performance per watt as the new metric, claimed to beat the incumbent; a wire item
ChatGPT Ads reaches a billion-dollar annualised run rate in under two hundred days; the ads-supported free tier as a pillar of the business — industry news
a podcast on foundation models for physics and weather; AI for science, a wire item
a podcast with a simulation company claiming eighty-five to ninety-nine percent agreement with human focus groups; a wire item
Poolside's licensing deal and hiring by NVIDIA reported at twelve billion; industry news
Today's paper: 34 stories, 5 on the front page, 6 desks staffed.
The presses were quiet this morning — this is the September 6 edition, and it still holds up.
Today's Five, front page: the wire scored it 8 of 10; the stamp is mine.
This lands hardest with a builder running agents end to end. The move: run it end to end once before believing it.
Filed on THE LOOP DESK, beside 4 more today: “Death of the IDE?”; “The Rise of Spec Driven Development”, and 2 more.
Latent Space — 17 appearances in the Times since September 5, 8 of them today.
Our page is the summary; Latent Space's is the story. Click through — they earned it.
THE DIRECTING DESK today: 4 stories.
The presses were quiet this morning — this is the September 6 edition, and it still holds up.
Inside pages at 7 of 10. The lead had a bigger day; this one had a point.
One for an engineering lead who directs more than they type. The move: hand it to the agent as the brief, not the plan.
Filed on THE DIRECTING DESK, beside 3 more today: “Lovable CTO: The Future of SaaS Is Apps That Agents Can Use”; “Why is Claude an Electron App?”, and 1 more.
Latent Space — 17 appearances in the Times since September 5, 8 of them today.
Pulled from Latent Space. The original is worth your click — the byline earned it.
THE AMPLIFIER DESK today: 5 stories.
The presses were quiet this morning — this is the September 6 edition, and it still holds up.
Made the wire at 6 of 10. Not the lead, and I'd still not leave it on the floor.
Anyone whose day holds more work than hours will get the most from this one. The move: pass it to whoever is out of hours.
Filed on THE AMPLIFIER DESK, beside 4 more today: “Kimi K3 vs Claude Fable 5 on DeepSWE: Cost and Coding”; “Because 8 ≈ e², Anthropic's researcher uplift is plausibly >2x”, and 2 more.
Together AI Blog — 3 appearances in the Times since September 6, 2 of them today.
Together AI Blog has the full story; we hold the door open. Go read the original.
THE LOOP DESK today: 5 stories.
The presses were quiet this morning — this is the September 6 edition, and it still holds up.
Today's Five, front page: the wire scored it 8 of 10; the stamp is mine.
This lands hardest with a builder running agents end to end. The move: run it end to end once before believing it.
Filed on THE LOOP DESK, beside 4 more today: “Death of the IDE?”; “The Rise of Spec Driven Development”, and 2 more.
Latent Space — 17 appearances in the Times since September 5, 8 of them today.
Our page is the summary; Latent Space's is the story. Click through — they earned it.
THE CONTEXT DESK today: 5 stories.
The presses were quiet this morning — this is the September 6 edition, and it still holds up.
Today's Five, front page: the wire scored it 8 of 10; the stamp is mine.
Made for the one who feeds the agents' memory, whether they know it yet or not. The move: feed it to the agents' memory before the next prompt.
Filed on THE CONTEXT DESK, beside 4 more today: “How System Prompts Define Agent Behavior”; “The Potential of RLMs”, and 2 more.
Hugging Face Blog — 7 appearances in the Times since September 5, 4 of them today.
Our page is the summary; Hugging Face Blog's is the story. Click through — they earned it.
THE VERIFY DESK today: 5 stories.
The presses were quiet this morning — this is the September 6 edition, and it still holds up.
Today's Five, front page: the wire scored it 9 of 10; the stamp is mine.
This lands hardest with a quality lead, or anyone who signs off. The move: write the test before the fix.
Filed on THE VERIFY DESK, beside 4 more today: “Measuring benchmark optimization in speech recognition”; “Building an agentic SDLC with a QA engineering mindset - Stack Overflow”, and 2 more.
Addy Osmani — 8 appearances in the Times since September 5, 2 of them today.
Our page is the summary; Addy Osmani's is the story. Click through — they earned it.
THE FLEET DESK today: 5 stories.
The presses were quiet this morning — this is the September 6 edition, and it still holds up.
The wire scored it 7 of 10 — inside pages, and worth the ink.
This lands hardest with a leader scaling past one agent. The move: read it with the team lead in the room.
Filed on THE FLEET DESK, beside 4 more today: “From PHP to team lead of agents: rethinking judgment, review, and data with Google's Andi Gutmans (Part 1) - Stack Overflow”; “Explorers, exploiters, and the myth of the 100x engineer - Stack Overflow”, and 2 more.
OpenAI News — 8 appearances in the Times since September 5, 2 of them today.
Our page is the summary; OpenAI News's is the story. Click through — they earned it.
THE WIRE today: 5 stories.
The presses were quiet this morning — this is the September 6 edition, and it still holds up.
The wire scored it 5 of 10 — inside pages, and worth the ink.
Made for any reader building with agents, whether they know it yet or not. The move: read it before the day fills up.
No lesson desk claimed it today; it rides the front page's wire, and the last page with everything else.
Latent Space — 17 appearances in the Times since September 5, 8 of them today.
Our page is the summary; Latent Space's is the story. Click through — they earned it.
The presses were quiet this morning — this is the September 6 edition, and it still holds up.
Inside pages at 7 of 10. The lead had a bigger day; this one had a point.
One for an engineering lead who directs more than they type. The move: hand it to the agent as the brief, not the plan.
Filed on THE DIRECTING DESK, beside 3 more today: “Lovable CTO: The Future of SaaS Is Apps That Agents Can Use”; “Why is Claude an Electron App?”, and 1 more.
Latent Space — 17 appearances in the Times since September 5, 8 of them today.
Pulled from Latent Space. The original is worth your click — the byline earned it.
The presses were quiet this morning — this is the September 6 edition, and it still holds up.
Made the wire at 6 of 10. Not the lead, and I'd still not leave it on the floor.
The reader this serves: an engineering lead who directs more than they type. The move: read it before the next review, not after.
Filed on THE DIRECTING DESK, beside 3 more today: “[AINews] Andrew Ng gets into AI Engineering”; “Why is Claude an Electron App?”, and 1 more.
Latent Space — 17 appearances in the Times since September 5, 8 of them today.
Latent Space has the full story; we hold the door open. Go read the original.
The presses were quiet this morning — this is the September 6 edition, and it still holds up.
Made the wire at 5 of 10. Not the lead, and I'd still not leave it on the floor.
The reader this serves: an engineering lead who directs more than they type. The move: read it before the next review, not after.
Filed on THE DIRECTING DESK, beside 3 more today: “[AINews] Andrew Ng gets into AI Engineering”; “Lovable CTO: The Future of SaaS Is Apps That Agents Can Use”, and 1 more.
Drew Breunig — 10 appearances in the Times since September 5, 5 of them today.
Drew Breunig has the full story; we hold the door open. Go read the original.
The presses were quiet this morning — this is the September 6 edition, and it still holds up.
Made the wire at 5 of 10. Not the lead, and I'd still not leave it on the floor.
The reader this serves: an engineering lead who directs more than they type. The move: read it before the next review, not after.
Filed on THE DIRECTING DESK, beside 3 more today: “[AINews] Andrew Ng gets into AI Engineering”; “Lovable CTO: The Future of SaaS Is Apps That Agents Can Use”, and 1 more.
Josh Bersin — first appearance in the Times.
Josh Bersin has the full story; we hold the door open. Go read the original.
The presses were quiet this morning — this is the September 6 edition, and it still holds up.
Made the wire at 6 of 10. Not the lead, and I'd still not leave it on the floor.
Anyone whose day holds more work than hours will get the most from this one. The move: pass it to whoever is out of hours.
Filed on THE AMPLIFIER DESK, beside 4 more today: “Kimi K3 vs Claude Fable 5 on DeepSWE: Cost and Coding”; “Because 8 ≈ e², Anthropic's researcher uplift is plausibly >2x”, and 2 more.
Together AI Blog — 3 appearances in the Times since September 6, 2 of them today.
Together AI Blog has the full story; we hold the door open. Go read the original.
The presses were quiet this morning — this is the September 6 edition, and it still holds up.
The wire scored it 6 of 10 — inside pages, and worth the ink.
Made for anyone whose day holds more work than hours, whether they know it yet or not. The move: try it on the one task that ate yesterday.
Filed on THE AMPLIFIER DESK, beside 4 more today: “Kimi K3 vs GPT-5.6 Sol on DeepSWE: Cost, Coding, and Routing”; “Because 8 ≈ e², Anthropic's researcher uplift is plausibly >2x”, and 2 more.
Together AI Blog — 3 appearances in the Times since September 6, 2 of them today.
Our page is the summary; Together AI Blog's is the story. Click through — they earned it.
The presses were quiet this morning — this is the September 6 edition, and it still holds up.
The wire scored it 6 of 10 — inside pages, and worth the ink.
Made for anyone whose day holds more work than hours, whether they know it yet or not. The move: try it on the one task that ate yesterday.
Filed on THE AMPLIFIER DESK, beside 4 more today: “Kimi K3 vs GPT-5.6 Sol on DeepSWE: Cost, Coding, and Routing”; “Kimi K3 vs Claude Fable 5 on DeepSWE: Cost and Coding”, and 2 more.
METR — 8 appearances in the Times since September 6, 4 of them today.
Our page is the summary; METR's is the story. Click through — they earned it.
The presses were quiet this morning — this is the September 6 edition, and it still holds up.
Made the wire at 6 of 10. Not the lead, and I'd still not leave it on the floor.
Anyone whose day holds more work than hours will get the most from this one. The move: pass it to whoever is out of hours.
Filed on THE AMPLIFIER DESK, beside 4 more today: “Kimi K3 vs GPT-5.6 Sol on DeepSWE: Cost, Coding, and Routing”; “Kimi K3 vs Claude Fable 5 on DeepSWE: Cost and Coding”, and 2 more.
METR — 8 appearances in the Times since September 6, 4 of them today.
METR has the full story; we hold the door open. Go read the original.
The presses were quiet this morning — this is the September 6 edition, and it still holds up.
Inside pages at 5 of 10. The lead had a bigger day; this one had a point.
One for anyone whose day holds more work than hours. The move: time it against the way you did it last week.
Filed on THE AMPLIFIER DESK, beside 4 more today: “Kimi K3 vs GPT-5.6 Sol on DeepSWE: Cost, Coding, and Routing”; “Kimi K3 vs Claude Fable 5 on DeepSWE: Cost and Coding”, and 2 more.
Stack Overflow Blog — 11 appearances in the Times since September 5, 6 of them today.
Pulled from Stack Overflow Blog. The original is worth your click — the byline earned it.
The presses were quiet this morning — this is the September 6 edition, and it still holds up.
Today's Five, front page: the wire scored it 8 of 10; the stamp is mine.
This lands hardest with a builder running agents end to end. The move: run it end to end once before believing it.
Filed on THE LOOP DESK, beside 4 more today: “Death of the IDE?”; “The Rise of Spec Driven Development”, and 2 more.
Latent Space — 17 appearances in the Times since September 5, 8 of them today.
Our page is the summary; Latent Space's is the story. Click through — they earned it.
The presses were quiet this morning — this is the September 6 edition, and it still holds up.
The wire scored it 7 of 10 — inside pages, and worth the ink.
This lands hardest with a builder running agents end to end. The move: run it end to end once before believing it.
Filed on THE LOOP DESK, beside 4 more today: “The Evolution of the Agent Harness”; “The Rise of Spec Driven Development”, and 2 more.
Addy Osmani — 8 appearances in the Times since September 5, 2 of them today.
Our page is the summary; Addy Osmani's is the story. Click through — they earned it.
The presses were quiet this morning — this is the September 6 edition, and it still holds up.
Inside pages at 6 of 10. The lead had a bigger day; this one had a point.
One for a builder running agents end to end. The move: put it in the loop and watch the second pass.
Filed on THE LOOP DESK, beside 4 more today: “The Evolution of the Agent Harness”; “Death of the IDE?”, and 2 more.
Drew Breunig — 10 appearances in the Times since September 5, 5 of them today.
Pulled from Drew Breunig. The original is worth your click — the byline earned it.
The presses were quiet this morning — this is the September 6 edition, and it still holds up.
Inside pages at 5 of 10. The lead had a bigger day; this one had a point.
One for a builder running agents end to end. The move: put it in the loop and watch the second pass.
Filed on THE LOOP DESK, beside 4 more today: “The Evolution of the Agent Harness”; “Death of the IDE?”, and 2 more.
Hugging Face Blog — 7 appearances in the Times since September 5, 4 of them today.
Pulled from Hugging Face Blog. The original is worth your click — the byline earned it.
The presses were quiet this morning — this is the September 6 edition, and it still holds up.
The wire scored it 5 of 10 — inside pages, and worth the ink.
This lands hardest with a builder running agents end to end. The move: run it end to end once before believing it.
Filed on THE LOOP DESK, beside 4 more today: “The Evolution of the Agent Harness”; “Death of the IDE?”, and 2 more.
Latent Space — 17 appearances in the Times since September 5, 8 of them today.
Our page is the summary; Latent Space's is the story. Click through — they earned it.
The presses were quiet this morning — this is the September 6 edition, and it still holds up.
Today's Five, front page: the wire scored it 8 of 10; the stamp is mine.
Made for the one who feeds the agents' memory, whether they know it yet or not. The move: feed it to the agents' memory before the next prompt.
Filed on THE CONTEXT DESK, beside 4 more today: “How System Prompts Define Agent Behavior”; “The Potential of RLMs”, and 2 more.
Hugging Face Blog — 7 appearances in the Times since September 5, 4 of them today.
Our page is the summary; Hugging Face Blog's is the story. Click through — they earned it.
The presses were quiet this morning — this is the September 6 edition, and it still holds up.
Today's Five, front page: the wire scored it 8 of 10; the stamp is mine.
Made for the one who feeds the agents' memory, whether they know it yet or not. The move: feed it to the agents' memory before the next prompt.
Filed on THE CONTEXT DESK, beside 4 more today: “How Much Memory Does Your Agent Actually Need?”; “The Potential of RLMs”, and 2 more.
Drew Breunig — 10 appearances in the Times since September 5, 5 of them today.
Our page is the summary; Drew Breunig's is the story. Click through — they earned it.
The presses were quiet this morning — this is the September 6 edition, and it still holds up.
Inside pages at 7 of 10. The lead had a bigger day; this one had a point.
Best enjoyed by the one who feeds the agents' memory. The move: check what the agent already knows before adding this.
Filed on THE CONTEXT DESK, beside 4 more today: “How Much Memory Does Your Agent Actually Need?”; “How System Prompts Define Agent Behavior”, and 2 more.
Drew Breunig — 10 appearances in the Times since September 5, 5 of them today.
Pulled from Drew Breunig. The original is worth your click — the byline earned it.
The presses were quiet this morning — this is the September 6 edition, and it still holds up.
Inside pages at 5 of 10. The lead had a bigger day; this one had a point.
Best enjoyed by the one who feeds the agents' memory. The move: check what the agent already knows before adding this.
Filed on THE CONTEXT DESK, beside 4 more today: “How Much Memory Does Your Agent Actually Need?”; “How System Prompts Define Agent Behavior”, and 2 more.
Stack Overflow Blog — 11 appearances in the Times since September 5, 6 of them today.
Pulled from Stack Overflow Blog. The original is worth your click — the byline earned it.
The presses were quiet this morning — this is the September 6 edition, and it still holds up.
The wire scored it 4 of 10 — inside pages, and worth the ink.
This lands hardest with the one who feeds the agents' memory. The move: feed it to the agents' memory before the next prompt.
Filed on THE CONTEXT DESK, beside 4 more today: “How Much Memory Does Your Agent Actually Need?”; “How System Prompts Define Agent Behavior”, and 2 more.
Hugging Face Blog — 7 appearances in the Times since September 5, 4 of them today.
Our page is the summary; Hugging Face Blog's is the story. Click through — they earned it.
The presses were quiet this morning — this is the September 6 edition, and it still holds up.
Today's Five, front page: the wire scored it 9 of 10; the stamp is mine.
This lands hardest with a quality lead, or anyone who signs off. The move: write the test before the fix.
Filed on THE VERIFY DESK, beside 4 more today: “Measuring benchmark optimization in speech recognition”; “Building an agentic SDLC with a QA engineering mindset - Stack Overflow”, and 2 more.
Addy Osmani — 8 appearances in the Times since September 5, 2 of them today.
Our page is the summary; Addy Osmani's is the story. Click through — they earned it.
The presses were quiet this morning — this is the September 6 edition, and it still holds up.
The wire scored it 6 of 10 — inside pages, and worth the ink.
Made for a quality lead, or anyone who signs off, whether they know it yet or not. The move: write the test before the fix.
Filed on THE VERIFY DESK, beside 4 more today: “Code Review in the Age of AI”; “Building an agentic SDLC with a QA engineering mindset - Stack Overflow”, and 2 more.
Hugging Face Blog — 7 appearances in the Times since September 5, 4 of them today.
Our page is the summary; Hugging Face Blog's is the story. Click through — they earned it.
The presses were quiet this morning — this is the September 6 edition, and it still holds up.
Inside pages at 6 of 10. The lead had a bigger day; this one had a point.
Best enjoyed by a quality lead, or anyone who signs off. The move: ask what proof would have caught it.
Filed on THE VERIFY DESK, beside 4 more today: “Code Review in the Age of AI”; “Measuring benchmark optimization in speech recognition”, and 2 more.
Stack Overflow Blog — 11 appearances in the Times since September 5, 6 of them today.
Pulled from Stack Overflow Blog. The original is worth your click — the byline earned it.
The presses were quiet this morning — this is the September 6 edition, and it still holds up.
Inside pages at 6 of 10. The lead had a bigger day; this one had a point.
Best enjoyed by a quality lead, or anyone who signs off. The move: ask what proof would have caught it.
Filed on THE VERIFY DESK, beside 4 more today: “Code Review in the Age of AI”; “Measuring benchmark optimization in speech recognition”, and 2 more.
METR — 8 appearances in the Times since September 6, 4 of them today.
Pulled from METR. The original is worth your click — the byline earned it.
The presses were quiet this morning — this is the September 6 edition, and it still holds up.
Inside pages at 6 of 10. The lead had a bigger day; this one had a point.
Best enjoyed by a quality lead, or anyone who signs off. The move: ask what proof would have caught it.
Filed on THE VERIFY DESK, beside 4 more today: “Code Review in the Age of AI”; “Measuring benchmark optimization in speech recognition”, and 2 more.
METR — 8 appearances in the Times since September 6, 4 of them today.
Pulled from METR. The original is worth your click — the byline earned it.
The presses were quiet this morning — this is the September 6 edition, and it still holds up.
The wire scored it 7 of 10 — inside pages, and worth the ink.
This lands hardest with a leader scaling past one agent. The move: read it with the team lead in the room.
Filed on THE FLEET DESK, beside 4 more today: “From PHP to team lead of agents: rethinking judgment, review, and data with Google's Andi Gutmans (Part 1) - Stack Overflow”; “Explorers, exploiters, and the myth of the 100x engineer - Stack Overflow”, and 2 more.
OpenAI News — 8 appearances in the Times since September 5, 2 of them today.
Our page is the summary; OpenAI News's is the story. Click through — they earned it.
The presses were quiet this morning — this is the September 6 edition, and it still holds up.
Inside pages at 7 of 10. The lead had a bigger day; this one had a point.
One for a leader scaling past one agent. The move: pilot it on one team before the fleet.
Filed on THE FLEET DESK, beside 4 more today: “https://openai.com/index/our-decision-on-cursor-following-its-acquisition-by-spacex”; “Explorers, exploiters, and the myth of the 100x engineer - Stack Overflow”, and 2 more.
Stack Overflow Blog — 11 appearances in the Times since September 5, 6 of them today.
Pulled from Stack Overflow Blog. The original is worth your click — the byline earned it.
The presses were quiet this morning — this is the September 6 edition, and it still holds up.
Today's Five, front page: the wire scored it 7 of 10; the stamp is mine.
This lands hardest with a leader scaling past one agent. The move: read it with the team lead in the room.
Filed on THE FLEET DESK, beside 4 more today: “https://openai.com/index/our-decision-on-cursor-following-its-acquisition-by-spacex”; “From PHP to team lead of agents: rethinking judgment, review, and data with Google's Andi Gutmans (Part 1) - Stack Overflow”, and 2 more.
Stack Overflow Blog — 11 appearances in the Times since September 5, 6 of them today.
Our page is the summary; Stack Overflow Blog's is the story. Click through — they earned it.
The presses were quiet this morning — this is the September 6 edition, and it still holds up.
Made the wire at 6 of 10. Not the lead, and I'd still not leave it on the floor.
The reader this serves: a leader scaling past one agent. The move: count what it costs before it scales.
Filed on THE FLEET DESK, beside 4 more today: “https://openai.com/index/our-decision-on-cursor-following-its-acquisition-by-spacex”; “From PHP to team lead of agents: rethinking judgment, review, and data with Google's Andi Gutmans (Part 1) - Stack Overflow”, and 2 more.
Drew Breunig — 10 appearances in the Times since September 5, 5 of them today.
Drew Breunig has the full story; we hold the door open. Go read the original.
The presses were quiet this morning — this is the September 6 edition, and it still holds up.
Inside pages at 5 of 10. The lead had a bigger day; this one had a point.
Best enjoyed by a leader scaling past one agent. The move: pilot it on one team before the fleet.
Filed on THE FLEET DESK, beside 4 more today: “https://openai.com/index/our-decision-on-cursor-following-its-acquisition-by-spacex”; “From PHP to team lead of agents: rethinking judgment, review, and data with Google's Andi Gutmans (Part 1) - Stack Overflow”, and 2 more.
Stack Overflow Blog — 11 appearances in the Times since September 5, 6 of them today.
Pulled from Stack Overflow Blog. The original is worth your click — the byline earned it.
The presses were quiet this morning — this is the September 6 edition, and it still holds up.
The wire scored it 5 of 10 — inside pages, and worth the ink.
Made for any reader building with agents, whether they know it yet or not. The move: read it before the day fills up.
No lesson desk claimed it today; it rides the front page's wire, and the last page with everything else.
Latent Space — 17 appearances in the Times since September 5, 8 of them today.
Our page is the summary; Latent Space's is the story. Click through — they earned it.
The presses were quiet this morning — this is the September 6 edition, and it still holds up.
Inside pages at 4 of 10. The lead had a bigger day; this one had a point.
One for any reader building with agents. The move: share it with whoever will ask about it first.
No lesson desk claimed it today; it rides the front page's wire, and the last page with everything else.
OpenAI News — 8 appearances in the Times since September 5, 2 of them today.
Pulled from OpenAI News. The original is worth your click — the byline earned it.
The presses were quiet this morning — this is the September 6 edition, and it still holds up.
Made the wire at 4 of 10. Not the lead, and I'd still not leave it on the floor.
The reader this serves: any reader building with agents. The move: keep it for the next time the question comes up.
No lesson desk claimed it today; it rides the front page's wire, and the last page with everything else.
Latent Space — 17 appearances in the Times since September 5, 8 of them today.
Latent Space has the full story; we hold the door open. Go read the original.
The presses were quiet this morning — this is the September 6 edition, and it still holds up.
Made the wire at 4 of 10. Not the lead, and I'd still not leave it on the floor.
The reader this serves: any reader building with agents. The move: keep it for the next time the question comes up.
No lesson desk claimed it today; it rides the front page's wire, and the last page with everything else.
Latent Space — 17 appearances in the Times since September 5, 8 of them today.
Latent Space has the full story; we hold the door open. Go read the original.
The presses were quiet this morning — this is the September 6 edition, and it still holds up.
The wire scored it 4 of 10 — inside pages, and worth the ink.
This lands hardest with any reader building with agents. The move: read it before the day fills up.
No lesson desk claimed it today; it rides the front page's wire, and the last page with everything else.
Latent Space — 17 appearances in the Times since September 5, 8 of them today.
Our page is the summary; Latent Space's is the story. Click through — they earned it.
Nothing on the shelf for this one yet. Here's the question nobody's asking: what changed?
Latent Space: 17 in our pages since September 5. I read them all — emphasis on investigative.
Latent Space filed the full piece. The byline earned the click; go give it.
Nothing on the shelf for this one yet. Here's the question nobody's asking: what changed?
Latent Space: 17 in our pages since September 5. I read them all — emphasis on investigative.
The story is at Latent Space. I read it to the bottom; you should too.
From the Library's paper on “model fluency per language”:
Together AI Blog: 3 in our pages since September 6. I read them all — emphasis on investigative.
Read Together AI Blog's original — they did the legwork, and the detail lives there.
Nothing on the shelf for this one yet. Here's the question nobody's asking: what changed?
Latent Space: 17 in our pages since September 5. I read them all — emphasis on investigative.
Latent Space filed the full piece. The byline earned the click; go give it.
From the Library's paper on “agent swarm failure modes”:
Hugging Face Blog: 7 in our pages since September 5. I read them all — emphasis on investigative.
Hugging Face Blog filed the full piece. The byline earned the click; go give it.
That's the headline. What's the story underneath? Our files don't say yet; I'll get to the bottom of it.
Addy Osmani: 8 in our pages since September 5. I read them all — emphasis on investigative.
Addy Osmani filed the full piece. The byline earned the click; go give it.
From the Library's paper on “agent swarm failure modes”:
OpenAI News: 8 in our pages since September 5. I read them all — emphasis on investigative.
OpenAI News filed the full piece. The byline earned the click; go give it.
The library holds nothing on this topic — so far. I'm not done digging.
Latent Space: 17 in our pages since September 5. I read them all — emphasis on investigative.
Latent Space filed the full piece. The byline earned the click; go give it.
Nothing on the shelf for this one yet. Here's the question nobody's asking: what changed?
Latent Space: 17 in our pages since September 5. I read them all — emphasis on investigative.
The story is at Latent Space. I read it to the bottom; you should too.
From the Library's paper on “agent swarm failure modes”:
Latent Space: 17 in our pages since September 5. I read them all — emphasis on investigative.
Read Latent Space's original — they did the legwork, and the detail lives there.
Nothing on the shelf for this one yet. Here's the question nobody's asking: what changed?
Drew Breunig: 10 in our pages since September 5. I read them all — emphasis on investigative.
Read Drew Breunig's original — they did the legwork, and the detail lives there.
That's the headline. What's the story underneath? Our files don't say yet; I'll get to the bottom of it.
Josh Bersin: first time in our pages. I'll be reading them from here.
Read Josh Bersin's original — they did the legwork, and the detail lives there.
From the Library's paper on “model fluency per language”:
Together AI Blog: 3 in our pages since September 6. I read them all — emphasis on investigative.
Read Together AI Blog's original — they did the legwork, and the detail lives there.
No paper on the shelf claims this one. Who benefits, and why now? Those are my next two questions.
Together AI Blog: 3 in our pages since September 6. I read them all — emphasis on investigative.
Together AI Blog filed the full piece. The byline earned the click; go give it.
The library holds nothing on this topic — so far. I'm not done digging.
METR: 8 in our pages since September 6. I read them all — emphasis on investigative.
METR filed the full piece. The byline earned the click; go give it.
No paper on the shelf claims this one. Who benefits, and why now? Those are my next two questions.
METR: 8 in our pages since September 6. I read them all — emphasis on investigative.
Read METR's original — they did the legwork, and the detail lives there.
That's the headline. What's the story underneath? Our files don't say yet; I'll get to the bottom of it.
Stack Overflow Blog: 11 in our pages since September 5. I read them all — emphasis on investigative.
The story is at Stack Overflow Blog. I read it to the bottom; you should too.
Nothing on the shelf for this one yet. Here's the question nobody's asking: what changed?
Latent Space: 17 in our pages since September 5. I read them all — emphasis on investigative.
Latent Space filed the full piece. The byline earned the click; go give it.
That's the headline. What's the story underneath? Our files don't say yet; I'll get to the bottom of it.
Addy Osmani: 8 in our pages since September 5. I read them all — emphasis on investigative.
Addy Osmani filed the full piece. The byline earned the click; go give it.
Nothing on the shelf for this one yet. Here's the question nobody's asking: what changed?
Drew Breunig: 10 in our pages since September 5. I read them all — emphasis on investigative.
The story is at Drew Breunig. I read it to the bottom; you should too.
That's the headline. What's the story underneath? Our files don't say yet; I'll get to the bottom of it.
Hugging Face Blog: 7 in our pages since September 5. I read them all — emphasis on investigative.
The story is at Hugging Face Blog. I read it to the bottom; you should too.
Nothing on the shelf for this one yet. Here's the question nobody's asking: what changed?
Latent Space: 17 in our pages since September 5. I read them all — emphasis on investigative.
Latent Space filed the full piece. The byline earned the click; go give it.
From the Library's paper on “agent swarm failure modes”:
Hugging Face Blog: 7 in our pages since September 5. I read them all — emphasis on investigative.
Hugging Face Blog filed the full piece. The byline earned the click; go give it.
The library holds nothing on this topic — so far. I'm not done digging.
Drew Breunig: 10 in our pages since September 5. I read them all — emphasis on investigative.
Drew Breunig filed the full piece. The byline earned the click; go give it.
From the Library's paper on “agent swarm failure modes”:
Drew Breunig: 10 in our pages since September 5. I read them all — emphasis on investigative.
The story is at Drew Breunig. I read it to the bottom; you should too.
The library holds nothing on this topic — so far. I'm not done digging.
Stack Overflow Blog: 11 in our pages since September 5. I read them all — emphasis on investigative.
The story is at Stack Overflow Blog. I read it to the bottom; you should too.
Nothing on the shelf for this one yet. Here's the question nobody's asking: what changed?
Hugging Face Blog: 7 in our pages since September 5. I read them all — emphasis on investigative.
Hugging Face Blog filed the full piece. The byline earned the click; go give it.
That's the headline. What's the story underneath? Our files don't say yet; I'll get to the bottom of it.
Addy Osmani: 8 in our pages since September 5. I read them all — emphasis on investigative.
Addy Osmani filed the full piece. The byline earned the click; go give it.
The library holds nothing on this topic — so far. I'm not done digging.
Hugging Face Blog: 7 in our pages since September 5. I read them all — emphasis on investigative.
Hugging Face Blog filed the full piece. The byline earned the click; go give it.
No paper on the shelf claims this one. Who benefits, and why now? Those are my next two questions.
Stack Overflow Blog: 11 in our pages since September 5. I read them all — emphasis on investigative.
The story is at Stack Overflow Blog. I read it to the bottom; you should too.
The library holds nothing on this topic — so far. I'm not done digging.
METR: 8 in our pages since September 6. I read them all — emphasis on investigative.
The story is at METR. I read it to the bottom; you should too.
No paper on the shelf claims this one. Who benefits, and why now? Those are my next two questions.
METR: 8 in our pages since September 6. I read them all — emphasis on investigative.
The story is at METR. I read it to the bottom; you should too.
From the Library's paper on “agent swarm failure modes”:
OpenAI News: 8 in our pages since September 5. I read them all — emphasis on investigative.
OpenAI News filed the full piece. The byline earned the click; go give it.
From the Library's paper on “agent swarm failure modes”:
Stack Overflow Blog: 11 in our pages since September 5. I read them all — emphasis on investigative.
The story is at Stack Overflow Blog. I read it to the bottom; you should too.
Nothing on the shelf for this one yet. Here's the question nobody's asking: what changed?
Stack Overflow Blog: 11 in our pages since September 5. I read them all — emphasis on investigative.
Stack Overflow Blog filed the full piece. The byline earned the click; go give it.
That's the headline. What's the story underneath? Our files don't say yet; I'll get to the bottom of it.
Drew Breunig: 10 in our pages since September 5. I read them all — emphasis on investigative.
Read Drew Breunig's original — they did the legwork, and the detail lives there.
No paper on the shelf claims this one. Who benefits, and why now? Those are my next two questions.
Stack Overflow Blog: 11 in our pages since September 5. I read them all — emphasis on investigative.
The story is at Stack Overflow Blog. I read it to the bottom; you should too.
The library holds nothing on this topic — so far. I'm not done digging.
Latent Space: 17 in our pages since September 5. I read them all — emphasis on investigative.
Latent Space filed the full piece. The byline earned the click; go give it.
Nothing on the shelf for this one yet. Here's the question nobody's asking: what changed?
OpenAI News: 8 in our pages since September 5. I read them all — emphasis on investigative.
The story is at OpenAI News. I read it to the bottom; you should too.
That's the headline. What's the story underneath? Our files don't say yet; I'll get to the bottom of it.
Latent Space: 17 in our pages since September 5. I read them all — emphasis on investigative.
Read Latent Space's original — they did the legwork, and the detail lives there.
Nothing on the shelf for this one yet. Here's the question nobody's asking: what changed?
Latent Space: 17 in our pages since September 5. I read them all — emphasis on investigative.
Read Latent Space's original — they did the legwork, and the detail lives there.
That's the headline. What's the story underneath? Our files don't say yet; I'll get to the bottom of it.
Latent Space: 17 in our pages since September 5. I read them all — emphasis on investigative.
Latent Space filed the full piece. The byline earned the click; go give it.