Skip to content
TEN Brief Ten verified stories a day 2026.11.20 KO

이 기사는 한국어로도 읽을 수 있습니다 →

Tech · 16 min read · Reference

What is an AI time horizon? 12 hours at 50%, 70 min at 80%

An AI time horizon is the length of task, measured by how long a human expert needs, that an AI model completes with a given probability. METR, a US nonprofit that evaluates AI systems, introduced it in a March 2025 paper and reports it at 50% and at 80% success. It does not mean the AI works alone for that long. It expresses task difficulty in human time. In METR public data read on November 20, 2026, Claude Opus 4.6 has a 50% horizon of about 12 hours and an 80% horizon of about 1 hour 10 minutes, and the 95% confidence interval on the 50% figure runs from 5 hours 17 minutes to 60 hours 34 minutes. The trend has doubled about every 6 to 7 months since 2019 and about every 4 months since 2023. The tasks lean heavily toward software, machine learning and security, and METR says measurements above 16 hours are unreliable with its current task suite.

A developer seen from behind at a desk with two monitors in a sunlit office, with an hourglass and a mug on the desk and a plain wall clock on a white wall

The three lines

  • Meaning — the human-expert time of tasks a model finishes with 50% (or 80%) probability; a unit of task difficulty, not of how long the AI runs
  • Numbers — in METR data read November 20, 2026, Claude Opus 4.6 is at about 12 hours at 50% and about 1 hour 10 minutes at 80%; the trend has doubled about every 4 months since 2023
  • Pitfalls — 50% success is not working reliability, the tasks are mostly software, and intervals are wide (5 to 60 hours); METR calls measurements above 16 hours unreliable

Key questions

what is an AI time horizon
**It is the length of task, measured in the time a human expert needs, that an AI model completes with a given probability. METR introduced it in March 2025. It measures task difficulty, not how long the AI works.** | Step | What happens | |---|---| | Task suite | 228 software, machine-learning and security tasks (Time Horizon 1.1) | | Human baseline | Experts attempt the same tasks; the times of successful attempts are combined by geometric mean | | AI runs | 6 independent runs per task, each scored as success or failure | | Curve fit | A logistic curve is fitted to success probability against the log of human time | | Read the horizon | The human time where the curve crosses 50% or 80% is the time horizon |
METR time horizon by model
**In METR public data (Time Horizon 1.1, read November 20, 2026), GPT-4 is at 4 minutes, GPT-5 at 3 hours 23 minutes and Claude Opus 4.6 at 11 hours 59 minutes. At 80% the figures are far shorter: 53 seconds, 38 minutes and 1 hour 10 minutes.** | Model (release) | 50% horizon | 80% horizon | |---|---|---| | GPT-4 (March 2023) | 4 min | 53 sec | | GPT-4o (May 2024) | 7 min | 1 min 16 sec | | Claude 3.7 Sonnet (February 2025) | 1 hr | 12 min | | GPT-5 (August 2025) | 3 hr 23 min | 38 min | | Claude Opus 4.5 (November 2025) | 4 hr 53 min | 49 min | | Claude Opus 4.6 (February 2026) | 11 hr 59 min | 1 hr 10 min | | GPT-5.4 (March 2026) | 5 hr 42 min | 54 min |
AI time horizon doubling every 7 months
**The original METR paper of March 2025 said about every 7 months since 2019. With the larger Time Horizon 1.1 task suite, the all-time figure is about 6 to 6.5 months and the figure since 2023 is about 4 months.** | Period | Time Horizon 1.0 | Time Horizon 1.1 (announced January 2026) | 1.1 current data (read November 20, 2026) | |---|---|---|---| | All-time (2019 on) | 195.8 days | 196.5 days | 187.8 days | | Since 2023 | 165.3 days | 130.8 days | 128.7 days (104 to 158) | | Since 2024 | 108.9 days | 88.6 days | Not in the data file |

An AI time horizon is the length of task, measured by how long it takes a human expert, that an AI model completes with a given probability. METR, a US nonprofit that evaluates AI systems, introduced it in a March 2025 paper. Saying a model has a 2-hour time horizon does not mean it works for two hours. It means the model succeeds about half the time on tasks that take a human expert about two hours. A benchmark score such as 84% is hard to translate into what kind of work a model can do. The time horizon converts that into a unit people already understand, and its chart has become the most cited picture in arguments and forecasts about how fast AI is improving.

This article explains how a time horizon is calculated, why the 50% and 80% horizons are so far apart, where the claim of doubling every 7 months came from and how it has since been revised, and what to watch for when reading the number. It ends with two figures from November 2026, an internal OpenAI statistic and a forecast from the AI Futures Project, and sets out how each differs from a time horizon. Every figure carries the date it was measured or checked.

1. What a time horizon is: definition and calculation

The METR definition: the task-completion time horizon is the task duration at which an AI agent is predicted to succeed with a given level of reliability, where duration is measured by human expert completion time. The calculation has five steps.

StepWhat happensDetail
Task suiteTasks of different lengths are assembledRE-Bench, HCAST and a set of short novel tasks, mostly software engineering, machine learning and cybersecurity. 170 tasks in the March 2025 version, 228 in the January 2026 version (Time Horizon 1.1)
Human baselineA human time is set for each taskContracted experts attempt the task with the same instructions and tools; the times of successful attempts are combined by geometric mean
AI runsThe model is given tools and the same tasksBy the METR description, 6 independent runs per task, with human review for reward hacking
Curve fitSuccess probability is modeled against human timeA logistic curve with the log of human time on the horizontal axis and success probability on the vertical
Read the horizonThe points where the curve crosses 50% and 80% are read offThe human time at those points is the 50% horizon and the 80% horizon

The fourth step is the core. A model solves nearly all short tasks and almost none of the long ones. The METR post of March 2025 said models then had near-100% success on tasks under about 4 minutes for a human and under 10% on tasks over about 4 hours. Somewhere in between the success rate passes 50%, and the time horizon marks that point as a task length.

Three clarifications. First, it has nothing to do with how long the AI actually takes. METR says agents are typically several times faster than humans on tasks they complete. Second, a task is a coherent unit of work that cannot be trivially split. Solving 1,000 one-hour math problems in a row is a one-hour task done 1,000 times, not a 1,000-hour task. Third, a 2-hour horizon does not mean every 2-hour task has a 50% success rate. METR explains that on tasks taking a human 90 minutes to 3 hours, GPT-5 always succeeded on about a third, always failed on about a third, and sometimes succeeded on the rest.

2. The 50% and 80% horizons: measurements by model

METR publishes both thresholds. The 50% horizon tolerates failing half the time. The 80% horizon requires four successes in five. The values below are from the Time Horizon 1.1 data file published by METR, downloaded on November 20, 2026. Figures in parentheses are bootstrap confidence intervals calculated by METR. Release dates are as recorded in the data file.

ModelReleased50% horizon (interval)80% horizon (interval)
GPT-2February 14, 2019About 3 secAbout 1 sec
GPT-3.5 Turbo InstructMarch 15, 2022About 36 secAbout 15 sec
GPT-4March 14, 20234 min (1.9 to 8 min)53 sec
GPT-4oMay 13, 20247 min (4 to 13 min)1 min 16 sec
Claude 3.5 Sonnet (new)October 22, 202421 min (10 to 41 min)2 min 36 sec
o1December 5, 202439 min (21 min to 1 hr 5 min)7 min
Claude 3.7 SonnetFebruary 24, 20251 hr (33 min to 1 hr 44 min)12 min
o3April 16, 20252 hr (1 hr 15 min to 3 hr 11 min)30 min
GPT-5August 7, 20253 hr 23 min (1 hr 53 min to 6 hr 46 min)38 min
Gemini 3 ProNovember 18, 20253 hr 44 min (2 hr 20 min to 6 hr 19 min)54 min
Claude Opus 4.5November 24, 20254 hr 53 min (2 hr 42 min to 10 hr 24 min)49 min
GPT-5.2December 11, 20255 hr 52 min (3 hr 18 min to 13 hr 35 min)1 hr 6 min
Claude Opus 4.6February 5, 202611 hr 59 min (5 hr 17 min to 60 hr 34 min)1 hr 10 min (27 min to 2 hr 50 min)
Gemini 3.1 ProFebruary 19, 20266 hr 24 min (3 hr 54 min to 11 hr 35 min)1 hr 30 min
GPT-5.4March 5, 20265 hr 42 min (3 hr 7 min to 12 hr 49 min)54 min
Claude Mythos Preview (early)April 7, 202617 hr 25 min (8 hr 29 min to 55 hr 4 min)3 hr 6 min (1 hr 37 min to 6 hr 39 min)

Three things stand out.

First, the 80% horizon is usually a quarter to an eighth of the 50% horizon. For Claude Opus 4.6 the gap is tenfold. A model that handles 12-hour tasks at the 50% standard can be trusted only up to 70-minute tasks at the 80% standard. Both statements about the same model are true: it does more than half a day of work, and it does a little over an hour of work. That is why it matters which number is being quoted.

Second, the intervals are wide. The point estimate for the 50% horizon of Opus 4.6 is about 12 hours, and the interval runs from 5 hours 17 minutes to 60 hours 34 minutes, more than an elevenfold spread. The stronger a model gets, the fewer tasks it fails, and the less data there is to pin down the right-hand end of the curve.

Third, the table stops here. When METR added Mythos Preview (early) on May 8, 2026, it attached a warning that measurements above 16 hours are unreliable with the current task suite. On September 8, 2026 it stated that the page is no longer actively updated. Time horizons for later models are not on the page. METR also says the list is not a complete record of the most capable models, and that limited capacity meant some were measured long after release and others skipped.

3. How fast it has grown: doubling every 7 months, and after

The metric became famous for its trend more than for any single value. On March 19, 2025, METR reported that the length of tasks generalist AI agents complete at 50% reliability had been doubling approximately every 7 months for six years. The same post noted that fitting only the 2024 and 2025 data gave a steeper trend, bringing the projected arrival of month-long tasks forward by about 2.5 years. The widely repeated extrapolation, that AI could carry out month-long projects on its own by the end of the decade if the trend held, comes from here.

On January 29, 2026, METR released Time Horizon 1.1, expanding the suite from 170 to 228 tasks: 73 added, 15 removed and 53 updated. Tasks taking a human 8 hours or more rose from 14 to 31, and evaluation moved from an in-house platform to Inspect, the open-source framework from the UK AI Security Institute. Doubling times changed as follows.

PeriodTime Horizon 1.0Time Horizon 1.1 (announced January 29, 2026)1.1 current data (read November 20, 2026)
All-time (2019 on)195.8 days (about 6.4 months)196.5 days (about 6.5 months)187.8 days (about 6.2 months)
Since 2023165.3 days (about 5.4 months)130.8 days (about 4.3 months)128.7 days (about 4.2 months; interval 104 to 158 days)
Since 2024108.9 days (about 3.6 months)88.6 days (about 2.9 months)Not in the data file

The all-time trend barely moved. Since 2023 it sped up to a doubling about every 4 months. Changing the tasks pushed older models down and newer models up. In the 1.1 announcement, the 50% horizon of GPT-4 (1106) fell 57%, from 8.5 to 3.6 minutes, and that of GPT-5 rose 55%, from 138 to 214 minutes. The models did not change. The ruler did, and the numbers moved that much, which says something about the nature of the metric.

The current data differ again from the 1.1 announcement because METR corrected a regularization mistake on March 3, 2026. According to the METR research note of March 20, 2026, the fix lowered the 50% horizons of recent models by up to 20%. The doubling times in the current data exclude measurements whose central estimate is above 16 hours.

4. Pitfalls when reading the number

PitfallDetailBasis
50% is not working reliabilityHalf the attempts fail. To know what can be handed off and left alone, look at the 80% horizon or higher, and the 80% horizon is a quarter to a tenth of the 50% oneTable in section 2. METR says it does not report a 99% horizon because that would need many more tasks
The tasks are mostly softwareSoftware, machine-learning and security tasks dominate, and they are well specified and automatically scored. METR says it found similar exponential trends in other domains with very different absolute valuesTask description and FAQ on the METR page
The human baseline is a person without contextThe baseliners are professionals with about 5 years of experience on average, seeing the task for the first time. METR suggests thinking of a 2-hour task as what a new hire or freelance contractor could do in 2 hours. Someone who knows the project would be faster, so human times are probably overestimatesMETR page
Long tasks often have no measured human timeOf the 31 tasks of 8 hours or more in 1.1, only 5 have human baselines. The UC Berkeley paper notes that measured human times were unobtainable or invalid for 29% of tasks, where an expert estimate was used1.1 announcement, arXiv 2610.12466
Intervals are wideThe 50% interval for Opus 4.6 runs from 5 to 60 hours. METR calls measurements above 16 hours unreliableMETR data file and page
Results depend on modeling choicesReasonable alternative curve shapes cut the 50% horizons of then-recent models by up to 35% and raise 80% horizons by up to 100%. Dropping the public tasks takes the 50% horizon of Opus 4.6 from 11 hours 59 minutes to 7 hours 11 minutesMETR research note (March 20, 2026)
Clean tasks are not real workMETR found that agents do worse on messier tasks, and that performance drops substantially when work is scored holistically, not algorithmically. It gives this as a reason an 8-hour horizon does not mean jobs can be automatedFAQ on the METR page

There is outside statistical criticism as well. In a paper posted to arXiv on October 8, 2026, On the estimation and validity of AI time horizons, Drew T. Nguyen and William Fithian of the UC Berkeley Department of Statistics reanalyzed the public METR data (228 tasks, 26 AIs). Their target is the assumption that the difficulty of a task for an AI rises linearly with the log of human time. Relaxing it with splines and item-response theory, they found the curve nearly flat between about 2 and 30 minutes of human time. Their reading: a jump in time horizon from 3 to 30 minutes is much easier than one from 30 minutes to 5 hours, though both are tenfold. A doubling is not the same amount of progress everywhere on the scale.

The paper does not dispute the exponential trend itself. The authors write that the observed exponential growth is empirical and that they do not challenge it. Their proposal is to stop reading a time horizon as a single point and to read it alongside diagnostic plots showing how human time maps to AI difficulty. It is a preprint and has not been peer reviewed. METR has acknowledged the underlying problem too: its March 2026 note says that as the task suite saturates, the results become more sensitive to analysis choices.

5. Two figures from November 2026: are they the same measurement?

Two things brought talk of AI doing tasks that take hours back into circulation in November 2026. Both sound like time horizons. They measure different things.

The internal OpenAI statistic. In a post published on November 18, 2026, OpenAI was reported to have said that the share of internal research tasks taking a human 2 to 4 hours that agents completed without human intervention rose from 23% in March 2026 to 46% in October. For 4-to-8-hour tasks the figures were 13% and 35%. Results varied sharply by type of work: 79% for monitoring training runs, 25% for writing inference and serving code. The OpenAI post itself could not be opened, so this rests on three outlets that agree.

The AI Futures Project forecast. The authors of the AI 2027 scenario wrote in a quarterly update dated November 10, 2026 that all of their forecasters now expect a superhuman AI researcher is likely to arrive some time in 2027, assuming no substantial deliberate slowdown. Eli Lifland gives a median of August 2027. That Daniel Kokotajlo moved his median from December 2028 to May 2027 was confirmed in secondary coverage only. The main evidence for the update is not time horizons. It is a separate METR report estimating that AI R&D at Anthropic is progressing at about twice its historical pace (range 1.3 to 3 times), with roughly 80% of that acceleration attributed to AI. The authors say most of the informative evidence was redacted and call their analysis highly preliminary. Their forecasting model has, however, used METR time horizon research as one of its inputs since its December 2025 version.

METR time horizonInternal OpenAI statistic (published November 18, 2026)AI Futures forecast (November 10, 2026)
What is measuredSuccess rate is fixed at 50% or 80% and the task length is solved forTask length is fixed (2 to 4 hours and so on) and the zero-intervention completion rate is countedNot a measurement. A probability distribution over when AI of a given capability arrives
TasksA fixed suite of 228 tasks; every model gets the same onesTasks researchers actually delegated to agents at work; the mix changes over timeNot applicable
Human timeMeasured by experts attempting the task (estimated for some)An estimate of human time; the method could not be confirmedNot applicable
Success criterionAutomatic scoring defined per taskFinished with no human intervention; how this was judged could not be confirmedNot applicable
Who measuresA third-party nonprofit, with data and code publicCompany figures, with no reproduction packageAn independent research group
Weak pointLimited to clean software tasks; unreliable above 16 hoursSelection effects. By the coverage, OpenAI itself cautions that researchers may have changed what they delegateDepends on model assumptions and redacted evidence

The two numbers cannot be read across. Translated loosely into time-horizon terms, 46% on 2-to-4-hour tasks sounds like a 50% horizon of around 3 hours, yet on the clean METR tasks public models from early 2026 were already measured at 50% horizons of about 6 to 12 hours. Real work comes with context and mess, and the bar is not passing a scorer but never needing a person to step in. The OpenAI figure shows performance in an actual workplace, which a time horizon cannot. The time horizon holds every model to the same ruler, which internal figures cannot. They are better read as filling each other's gaps.

6. Frequently asked questions

Does a 12-hour time horizon mean the AI works alone for 12 hours? No. It means the model succeeds about half the time on tasks that take a human expert about 12 hours. The time the AI actually takes is a separate matter, and METR says agents are typically several times faster than humans on tasks they complete.

Which should I look at, the 50% or the 80% horizon? It depends on the question. For where the frontier of capability sits, the 50% horizon. For the range of work that needs less human checking, the 80% horizon. METR says the trends for the two are very similar: the levels differ and the growth rate is the same.

Does an 8-hour horizon mean AI can replace a day of work? METR says no, for three reasons. The human baseline is a person without context. The tasks lean toward software. And most jobs are not made of well-specified tasks that can be scored automatically.

Why is there no 99% horizon? METR explains that measuring it accurately would take many more tasks, that those tasks would have to be very short and so harder to baseline reliably, and that the result would be much more sensitive to a single broken task.

If the trend continues, when does AI do month-long work? The original March 2025 paper extrapolated to around the end of the decade if the trend held. That is an extension of a line, not a measurement. The current task suite runs out at about 16 hours, and measuring beyond that needs longer tasks and people who have actually completed them. Whether the trend has bent or steepened above that point cannot be told with the current ruler.

What should be read alongside a time horizon? That one model can score very differently on different tests is already well documented for coding benchmarks. Tests built from real user change requests, completion rates that companies publish from internal use, and the share of AI-written changes that maintainers actually accept are different kinds of evidence, and they belong side by side.

7. What remains open or unconfirmed

ItemConfirmedNot confirmed
Definition and methodMETR page and the March 2025 paperNothing outstanding
Measurements by modelMETR data file (Time Horizon 1.1), downloaded and read on November 20, 2026Time horizons for models released after May 2026, which are not on the METR page
Mythos Preview (early)50% horizon about 17 hours 25 minutes, 80% horizon about 3 hours 6 minutesThe 50% figure is above the 16 hours METR calls unreliable
Doubling timeAbout 7 months in the original paper; 196.5, 130.8 and 88.6 days in the 1.1 announcement; 187.8 and 128.7 days in current dataThe current value of the trend since 2024; the trend above the 16-hour limit
METR page no longer updatedStated on the page on September 8, 2026The reason, and any schedule for a successor task suite
Statistical criticismThe abstract and opening pages of arXiv 2610.12466; the flat region from 2 to 30 minutesPeer review; the full set of revised estimates by model
Internal OpenAI statistic23% to 46% and 13% to 35%, reported consistently by three outletsThe post itself could not be opened; measurement period, how human time was estimated, how completion was judged
AI Futures forecastThe November 10, 2026 post, the statement that all forecasters expect 2027, the Lifland median of August 2027The size of the move for Kokotajlo comes from secondary coverage; the later part of the post was not read
Time horizons in other domainsMETR says it found exponential trends in other domainsAbsolute values by domain, which were not checked for this article

The debate over AI accelerating AI research is covered in our October 16, 2026 explainer on recursive self-improvement. Why one model gets different scores on different tests is in our August 17, 2026 explainer on coding benchmarks and our November 10, 2026 report on AI coding agent success rates. How a model with tools carries out a task is in our August 26, 2026 explainer on AI agents, and the definitions of the goal these metrics point toward are in our September 4, 2026 explainer on AGI. The internal OpenAI figures are covered in detail in our separate November 20, 2026 report on the OpenAI research acceleration post.

Sources

  1. METR — Task-Completion Time Horizons of Frontier AI Models (last updated 2026-09-08)
  2. METR — Time Horizon 1.1 raw results (benchmark_results_1_1.yaml, read 2026-11-20)
  3. METR — Time Horizon 1.0 raw results (benchmark_results_1_0.yaml, read 2026-11-20)
  4. METR — Measuring AI Ability to Complete Long Tasks (2025-03-19)
  5. arXiv 2503.14499 — Measuring AI Ability to Complete Long Software Tasks (2025-03-18)
  6. METR — Time Horizon 1.1 (2026-01-29)
  7. METR — Impact of modelling assumptions on time horizon results (2026-03-20)
  8. arXiv 2610.12466 — On the estimation and validity of AI time horizons: a statistical look at the METR plot (2026-10-08)
  9. AI Futures Project — Q3.5 Timelines Update: Looks Like the Intelligence Explosion Will Happen in 2027 After All (2026-11-10)
  10. Crypto Briefing — AI 2027 authors now expect a superhuman AI researcher in 2027 (2026-11-11)
  11. Wikipedia — AI Futures Project (last edited 2026-11-01)
  12. AI News Weekly — OpenAI Says Coding Agents Finish 46% of 2-4 Hour Research Tasks (2026-11-19)
  13. explainx.ai — OpenAI Agents Hit 46% on 2–4h Research Tasks (2026-11-19)
  14. Blockchain.News — OpenAI Reports Uneven Progress in AI-Driven Research Acceleration (2026-11-19)
  15. AI 2027 Tracker — METR doubling (last updated 2026-11-07)

Verification

Published
Last modified
Cross-check
Checked against 15 independent sources.
Unverified
  • The OpenAI post of November 18, 2026, Research acceleration: The jagged frontier, could not be opened (HTTP 403). The figures of 23% to 46% for 2-to-4-hour tasks and 13% to 35% for 4-to-8-hour tasks come from three outlets that agree: AI News Weekly, explainx.ai and Blockchain.News. The outlets describe the measurement period differently (March to October 2026 in two, August 1 to October 18 in one). How human task time was estimated and how completion was judged could not be confirmed.
  • Only the first part (about 100,000 characters) of the AI Futures Project post of November 10, 2026 was read. The statement that all forecasters expect a superhuman AI researcher (SAR) some time in 2027, and the SAR median of August 2027 for Eli Lifland, were seen in the post itself. The move of the median for Daniel Kokotajlo from December 2028 to May 2027 was seen in secondary coverage only. In the part read, the post does not cite time horizons as its evidence.
  • Figures in the Time Horizon 1.1 announcement (January 29, 2026) differ from the current public data because METR corrected a regularization mistake on March 3, 2026. For example, the 50% horizon of GPT-5 is 214 minutes in the announcement and about 203 minutes (3 hours 23 minutes) in the current data, while the FAQ on the METR page still shows 2 hours 17 minutes, which appears to be from the older version. The tables here follow the data file downloaded on November 20, 2026.
  • The upper bound of the confidence interval on the 50% horizon of Claude Opus 4.6 is about 60.6 hours in the METR data file. The AI 2027 Tracker, citing a March 2026 analysis by Ajeya Cotra, gives 5.3 to 66 hours. This article follows the METR data file.
  • The 50% horizon of about 17 hours 25 minutes for Claude Mythos Preview (early) is above the 16 hours that METR itself calls unreliable. Time horizons for later models (Claude Opus 5.5, Fable 5.2, the GPT-6 family and others) are not on the METR page.
  • The METR page does not say why it is no longer actively updated. Saturation of the task suite is an inference from the March 2026 METR research note and the 16-hour warning.
  • Figures from the METR Frontier Risk Report of May 2026 (such as a 105-day doubling time since 2024) were seen only on the AI 2027 Tracker. The report was not opened, so they are not used in the text.
  • arXiv 2610.12466 is a preprint that has not been peer reviewed, and only the abstract and first six pages were read. The change in the GPT-4o horizon from 7.2 minutes under the baseline model to 4.4 minutes under the new model was read from Figure 1 of the paper. Revised estimates for other models were not checked.
  • The count of 170 tasks in the original paper comes from the METR Time Horizon 1.1 announcement (170 to 228); the arXiv abstract gives no total. A confidence interval for the figure of about 7 months was not confirmed in the paper itself. The all-time estimate in the Time Horizon 1.0 data file is 201 days (176 to 225).
  • Conversions of doubling times from days to months (for example 128.7 days to about 4.2 months) are our own arithmetic, using 30.44 days per month.
Authoring
Reviewed by a person before publication. The full process is described in the Editorial.

Ten stories, once each morning

We send the three-line summaries only; the full pieces stay on the site. One-click unsubscribe, any time.

Related