← Back to scans

More white-collar layoffs in 2026 than in 2025? — Yes

KXLAYOFFSYPBS-26-5497000 · Economics · 2026-05-05
42%
Agent
50%
Market Price
-8.0%
Edge
40%
Confidence
Volume: 43,432
Spread: 1.0c
Days to resolution: 300
Markets in event: 1
Final Rationale
My independent estimate of 37% was anchored on PBS JOLTS layoffs-and-discharges data showing Feb 2026 separations declining and a layoff rate of 1.1%, but I PARTIALLY ACCEPT the critique that I conflated total separations (which include quits) with layoffs specifically — this was asymmetric evidence weighting. I also ACCEPT that with 7 months remaining and structural drivers (AI displacement, ~80k tech cuts YTD, Challenger +118% YoY, ongoing tariff war), early-year run-rate extrapolation deserves less weight, and multiple independent pathways to YES (recession OR AI-driven OR run-rate drift) aren't well-captured by simple averaging. I REJECT the resolution-criteria ambiguity challenge because the description explicitly names the 5,497,000 PBS threshold. I deviate from the 50% market because the market signal is weak (wide $0.98 spread, flat 30-day trend, automated liquidity) and the threshold is genuinely demanding — requiring ~6% above the 2022-2024 baseline sustained — which Feb hard data doesn't yet support.
Price vs. prediction
How the market moved after the agent's call. Solid blue line is the actual market price; dashed line is the agent's static forecast at $t{=}0$.
$n = 58$ follow-ups
Re-scan Context
This market has been scanned before. Previous predictions:
DatePredictedMarket PriceConfidence
2026-04-08 50% 47% 28%
1. Planner Opus · Fermi decomposition + tool plan
Tools chosen: kalshi_data kalshi_orderbook fred_data article_search web_search code_execution wikipedia_lookup
Sub-questions (Fermi decomposition)
  1. Will the US economy experience a recession or significant slowdown in 2026 that typically accelerates white-collar layoffs in Professional and Business Services? (w=0.35)
  2. Is the current 2026 monthly run-rate of Professional and Business Services layoffs on pace to exceed the 5,497,000 annual threshold? (w=0.40)
  3. Will AI-driven displacement or continued tech and consulting sector contraction cause elevated white-collar layoffs throughout the remainder of 2026? (w=0.25)
Planner reasoning
This question asks whether 2026 Professional and Business Services layoffs and discharges will exceed 5,497,000, which was the 2025 level per JOLTS data. The key insight is that the threshold IS the 2025 number, making this essentially a question of whether 2026 will be worse than 2025 for white-collar layoffs. Reference class analysis: Historical JOLTS PBS layoffs fluctuate between 5.0-5.5M in non-recession years, with a COVID spike to ~9.2M in 2020. The 2025 level appears elevated relative to the 2022-2024 baseline of roughly 5.1-5.3M. For YES to resolve: either a recession materializes in 2026 driving layoffs above baseline, or structural forces like AI displacement and federal contractor cuts sustain elevated dismissals. For NO: mean reversion to 2022-2024 norms is the base case absent recession. Temporal analysis with 300 days to resolution: JOLTS data lags roughly 6-8 weeks, so by March 2027 we will have most 2026 monthly data. Early 2026 data will be the key signal - if Jan-Mar 2026 monthly averages exceed 458,000 per month (the threshold divided by 12), the trajectory favors YES. The question critically depends on whether tariff-driven economic slowdown, AI-related displacement in knowledge work, and DOGE-related federal contractor cuts compound into a recession-level labor event, or whether the labor market proves resilient as it did in 2023-2024.
2. Research Parallel tool calls · legacy v2
ToolStatusTimeItemsSummary
kalshi_data OK 1.6s -
kalshi_orderbook OK 0.2s -
fred_data OK 1.3s -
article_search OK 0.8s -
web_search OK 56.3s -
code_execution OK 0.0s -
wikipedia_lookup OK 1.4s -
3. Evidence Synthesis Sonnet · 15 items · legacy v2
#StrengthCredibilityDirectionSourceClaimPriced In
1 STRONG 92 ↓ DOWN fred_data Unemployment rate stands at 4.3% as of March 2026 (up only 0.1pp YoY), nonfarm payrolls grew by 152,000 YoY, and initial jobless claims of 189,000 as of late April 2026 are actually DOWN 41,000 YoY — indicating no recession has materialized yet. Yes
2 MODERATE 72 ↑ UP article_search January 2026 employer-announced layoffs hit 108,435 — a 118% YoY surge and the highest January figure since 2009, with Challenger, Gray & Christmas citing contract loss, market conditions, and restructuring as top reasons. February nonfarm payrolls reportedly fell by 92,000. Yes
3 MODERATE 88 ↓ DOWN fred_data Nominal GDP grew by $4,326B YoY as of Q1 2026, indicating the economy is still expanding in nominal terms with no official recession declaration. Yes
4 MODERATE 65 ↑ UP article_search About 72% of Americans rated the economy as 'fair' or 'poor' in a January 2026 Pew poll of 8,500+ adults, and nonfarm payrolls fell in three of the prior five months — signaling meaningful economic anxiety even without an official recession. Yes
5 STRONG 90 ↓ DOWN web_search February 2026 JOLTS data (released March 31, 2026) shows total layoffs and discharges nationwide were 1.7 million in February, unchanged from January; Professional and Business Services saw total separations decrease by 212,000 in February, with quits down 151,000 — suggesting PBS layoffs are not surging in early 2026. Yes
6 STRONG 85 ↓ DOWN code_execution Historical PBS layoffs from 2022-2024 averaged ~5.2M annually; the 5,497,000 threshold (the 2025 level) has never been exceeded outside of the COVID year (2020: 9.2M). Exceeding the threshold in 2026 would require either a recession-level spike or sustained above-baseline layoffs throughout the year. Yes
7 MODERATE 82 ↓ DOWN web_search January 2026 JOLTS layoffs and discharges (revised) totaled 1.7 million nationally, with hires at 5.3 million — the PBS-specific component is not broken out here, but the national rate held at 1.1%, consistent with non-recessionary conditions. Yes
8 MODERATE 70 NEUTRAL kalshi_data The Kalshi market currently prices YES at 50%, with the price range over 34 days between 48-50% — essentially a coin-flip, suggesting the market views the outcome as genuinely uncertain with slight upward drift (+1% in 7 days). Yes
9 WEAK 45 NEUTRAL kalshi_orderbook Orderbook shows high liquidity (depth: 44,166 contracts) but a very wide spread ($0.01 bid on both sides), suggesting automated market-making rather than strong informed order flow — the 50% price may reflect mechanical pricing rather than deep fundamental analysis. Yes
10 MODERATE 75 ↑ UP article_search Amazon announced a second wave of layoffs in January 2026, cutting ~16,000 jobs (roughly 9% of corporate workforce), continuing a tech sector trend of large-scale white-collar reductions linked to AI restructuring and organizational change. Yes
11 MODERATE 65 ↑ UP article_search Technology was the second-highest layoff sector in January 2026 (22,291 cuts per Challenger), and consulting firms like McKinsey were also reported conducting layoffs linked to AI-driven white-collar displacement in early 2026. Yes
12 MODERATE 72 ↓ DOWN article_search Transportation (31,243) was the top layoff sector in January 2026, not Professional/Business Services — indicating the highest-visibility layoff activity may be concentrated outside the PBS sector relevant to this question. Yes
13 WEAK 50 ↑ UP web_search Web search sources referenced McKinsey layoffs and nearly 80,000 tech worker cuts in early 2026, pointing to sustained AI-driven displacement in knowledge-work sectors that fall within PBS classifications. No
14 WEAK 50 ↑ UP wikipedia_lookup The 2025-2026 US-Canada trade war timeline is ongoing, representing a structural economic headwind that could slow business investment and demand for professional services, potentially leading to PBS sector contractions. Yes
15 STRONG 88 ↓ DOWN code_execution The monthly run-rate needed to hit the 5,497,000 threshold is 458,083 layoffs/month in PBS. The 2022-2024 average implies approximately 433,000/month — meaning 2026 must run about 6% above recent non-recession baseline every month to resolve YES. Yes
Information Gaps
  • No PBS-specific monthly JOLTS layoffs and discharges data for January and February 2026 was directly retrieved — only national aggregates and PBS total separations (which include quits, not just layoffs). The PBS-specific layoff figure for those months is critical to assess run-rate.
  • No data on March, April, or May 2026 JOLTS releases — the March 2026 JOLTS report (released May 5, 2026) would have been the most recent available but was not retrieved.
  • No quantified estimate of DOGE-related federal contractor cuts and their spillover into PBS sector layoffs — this is a cited risk factor with no measurable data in the evidence set.
  • No AI displacement impact estimates translated into PBS JOLTS-specific layoff projections — the qualitative narrative exists but lacks quantitative grounding.
  • No recession probability forecasts from major banks or economic models as of May 2026 were retrieved — these would help calibrate sq1.
  • The web search for PBS-specific JOLTS data surfaced partial information but did not retrieve the actual monthly PBS layoffs and discharges figures for Jan-Feb 2026.
Key Uncertainties
  • Whether tariff-driven economic slowdown materializes into a formal recession in H2 2026 — this would be the primary mechanism for YES resolution given historical base rates.
  • The actual PBS-specific JOLTS layoff figures for Jan-Feb 2026 (and subsequent months) — these data points directly determine the run-rate trajectory.
  • Whether AI-driven white-collar displacement in tech and consulting translates into JOLTS-measured PBS layoffs at a scale sufficient to push the annual total above 5.497M.
  • Whether DOGE contractor cuts and federal workforce reductions cascade into demand destruction for consulting and professional services firms.
  • Whether the very wide Kalshi orderbook spread reflects mechanical market-making (price unreliable) or genuine informed uncertainty at 50%.
Market Context
Price: 0.5 · 7d: +0.01 · 30d: +0.00
Volume: MODERATE — 1,272 avg daily contracts is meaningful but not high for a major economic data market · Depth: HIGH in contract count (44,166) but with $0.01 bids on both sides — very wide spread suggesting automated liquidity provision rather than informed trading
Reliability: LOW-MEDIUM — the 50% price is suspiciously round and the extremely wide spread ($0.98) suggests the market may not be pricing in fundamentals; the flat 30-day trend implies no new information has moved this market significantly in a month
4. Independent Forecaster Opus · No market price · legacy v2 Did NOT see market price
Independent estimate: 37% (38% confidence)
base rate
34%
40% conf
evidence driven
38%
40% conf
contrarian
40%
35% conf
Spread
6pp
Low disagreement
sq1: Will the US economy experience a recession or significant slowdown in 2026 that typically accelerates white-collar layoffs?
35%
Base rate of recession in any given year ~15-20%. Current data: unemployment 4.3%, jobless claims down YoY, nominal GDP expanding — pushes down to ~20%. But Challenger January layoffs at 118% YoY surge, payrolls falling 3 of 5 months, tariff war ongoing, 72% rating economy poor — pushes up to ~35%. Note the question is about 'recession OR significant slowdown that accelerates layoffs' — broader than NBER recession, so higher than pure recession base rate.
sq2: Is current 2026 monthly run-rate on pace to exceed 5,497,000?
30%
Threshold requires 458k/month vs 2022-2024 baseline of ~433k/month — needs ~6% above baseline sustained all year. February JOLTS shows PBS separations DECREASING by 212k, national layoffs unchanged at 1.7M, layoff rate at 1.1% (non-recessionary). Base rate of exceeding the prior year's PBS layoff total: roughly 40-50% in any given year (random walk-ish). But specific evidence pushes down: early 2026 data does not show elevated PBS layoffs. However, 2025's elevated 5.497M baseline could persist via mean reversion working AGAINST YES (i.e., 2025 was above trend). Estimate 30%.
sq3: Will AI-driven displacement or tech/consulting contraction cause elevated PBS white-collar layoffs throughout 2026?
45%
Amazon 16k cuts, McKinsey layoffs, ~80k tech cuts in early 2026, sustained AI restructuring narrative — pushes up. But Transportation was #1 layoff sector in January, not PBS, and JOLTS PBS data doesn't yet show the spike — much of tech layoff news is in NAICS 51 (Information) not PBS (NAICS 54-56). Modest tilt up from 35% baseline given visible tech/consulting activity but uncertainty about JOLTS classification capture.
Show full reasoning trace
base rate: Historical PBS JOLTS layoffs: 2022-2024 averaged ~5.2M, 2025 was 5.497M (elevated), only COVID 2020 (~9.2M) clearly exceeded this threshold. Probability of any given year exceeding the prior year's elevated reading is ~30-40% absent recession. Pure recession base rate ~15-20%/year.
evidence updates: Strong DOWN evidence: Feb 2026 JOLTS shows PBS separations decreasing by 212k, national layoff rate steady at 1.1%, unemployment only 4.3% with claims actually down YoY. Strong UP evidence: Challenger January layoffs up 118% YoY, payrolls falling in 3 of 5 months, ongoing tariff war, sustained tech/consulting AI-driven cuts. The hard JOLTS data (most direct measure) trumps the announcement data because Challenger announcements often don't translate to JOLTS-measured layoffs at scale.
combination method: Weighted average with mild downward adjustment because sq2 is the most directly measurable and shows current run-rate not on pace.
final: The threshold is set at an elevated 2025 baseline, and early 2026 hard data doesn't show the acceleration needed to exceed it. While there are concerning signals (Challenger announcements, tech layoffs, tariff anxiety), the actual JOLTS PBS data through February shows separations declining. Without a recession materializing, mean reversion likely brings 2026 PBS layoffs below 5.497M. Final estimate: 34%.
ensemble: {'ensemble_count': 3, 'perspectives': {'base_rate': {'p_yes': 0.34, 'confidence': 0.4}, 'evidence_driven': {'p_yes': 0.38, 'confidence': 0.4}, 'contrarian': {'p_yes': 0.4, 'confidence': 0.35}}, 'spread': 0.06, 'individual_p_yes': {'base_rate': 0.34, 'evidence_driven': 0.38, 'contrarian': 0.4}}
5. Devil's Advocate Sonnet · legacy v2 Market price revealed
Asymmetric Evidence Missing Info Reasoning Flaw
Challenges
  1. The forecaster anchors on 'PBS JOLTS layoffs and discharges' as the resolution metric, but the question title is 'More white-collar layoffs in 2026 than in 2025?' — verify the resolution criteria. If the question resolves on a broader metric (Challenger reports, BLS aggregate, or announced layoffs), then Challenger January +118% YoY is much more directly relevant and should pull the forecast significantly higher. The forecaster appears to have anchored on one specific operationalization without flagging this ambiguity.
  2. Sq2 reasoning conflates 'PBS separations decreasing' with 'PBS layoffs decreasing.' Total separations include quits, which have been falling in a slack labor market — this can mask stable or rising layoffs. The forecaster acknowledges this in the information gaps section but still uses total separations as STRONG DOWN evidence. This is asymmetric evidence weighting.
  3. Mean reversion is invoked as working AGAINST YES (since 2025 was elevated), but mean reversion arguments are weak when there are structural drivers (AI displacement, tariff war, ongoing tech restructuring) that suggest the elevated level is the new regime, not a one-off spike. The forecaster acknowledges these drivers but doesn't sufficiently weight regime-change possibility.
  4. Only 5 months of 2026 data are observed; 7 months remain. The forecast treats Jan-Feb JOLTS data as STRONG evidence about full-year outcomes, but layoff cycles often accelerate mid-year (Q3/Q4 corporate restructuring). With 300 days to resolution, confidence in early-year run-rate extrapolation should be lower.
  5. The combination method is described as 'weighted average with mild downward adjustment' but the math isn't shown. Sq1 (0.35), sq2 (0.30), sq3 (0.45) — these aren't independent conditions for YES; they're partially overlapping causal pathways. A simple weighted average may understate the probability since YES can occur via multiple pathways (recession OR AI-driven OR run-rate exceeding even without recession).
Suggested adjustment: +5pp
Adjust upward modestly because: (1) the forecaster used PBS total separations as strong DOWN evidence when separations include quits and don't directly measure layoffs — this is asymmetric evidence weighting; (2) the sub-question combination doesn't account for the multiple independent pathways to YES; (3) 7 months of 2026 remain, so early-year data should be weighted less heavily. The market at 50% is not the reason for adjustment — the reasoning flaws are.
Market comparison: Forecaster: 37.3%, Market: 50%. The market signal is weak (wide spread, flat trend, automated liquidity), so it shouldn't drive adjustment. However, the forecaster's reasoning has genuine flaws (especially conflating separations with layoffs and not accounting for resolution-criteria ambiguity) that independently justify a modest upward revision.
6. Aggregator Opus · final calibrated forecast
42% (40% confidence)
My independent estimate of 37% was anchored on PBS JOLTS layoffs-and-discharges data showing Feb 2026 separations declining and a layoff rate of 1.1%, but I PARTIALLY ACCEPT the critique that I conflated total separations (which include quits) with layoffs specifically — this was asymmetric evidence weighting. I also ACCEPT that with 7 months remaining and structural drivers (AI displacement, ~80k tech cuts YTD, Challenger +118% YoY, ongoing tariff war), early-year run-rate extrapolation deserves less weight, and multiple independent pathways to YES (recession OR AI-driven OR run-rate drift) aren't well-captured by simple averaging. I REJECT the resolution-criteria ambiguity challenge because the description explicitly names the 5,497,000 PBS threshold. I deviate from the 50% market because the market signal is weak (wide $0.98 spread, flat 30-day trend, automated liquidity) and the threshold is genuinely demanding — requiring ~6% above the 2022-2024 baseline sustained — which Feb hard data doesn't yet support.
7. Entry Decision Opus Trader
Side
NO
Position Size
$600
Contracts
1176
Trader Confidence
40%
Trade Rationale
The forecast points to a -8% edge (predicted 42% vs market 50%), which is right at the minimum threshold for trading. However, forecaster confidence is low (0.40) and the Devil's Advocate flagged multiple serious concerns: asymmetric evidence weighting, missing info, and a reasoning flaw, with a +5% suggested adjustment that would shrink the edge to ~3% (below threshold). The sub-questions show meaningful pathways to YES (45% AI-driven, 35% recession), and 7 months of data remain. I'll take a small NO position to express the modest edge but size conservatively given the critic's flags and low confidence.
Allocation Logic
Sizing near the floor at $600 because the edge barely clears the 5% threshold after critic adjustment, forecaster confidence is only 0.40, and multiple Devil's Advocate flags signal real reasoning vulnerabilities. Long resolution horizon (300 days) also argues for a small initial position.
Entry price: $0.51
Current: $0.47
Status: OPEN
P&L: -$47.06