Tap a claim on the ring to put it at the centre.
← The IMO already feels like ancient history as an AI benchmark, as AI has moved into research mathematics.
17 connected korrents · 15 moments from 11 Nov 2024 to 16 Oct 2026. Nearly all of them are about benchmarks .
Everything filed under mathematics
mathematics
Everything filed under scaling laws
scaling laws
Everything filed under Anthropic
Anthropic
Everything filed under inflation
inflation
Everything filed under coding agents
coding agents
Everything filed under compilers
compilers
Everything filed under AI alignment
AI alignment
Everything filed under OpenAI
OpenAI
Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject Same subject
Read this korrent: The IMO already feels like ancient history as an AI benchmark, as AI has moved into research mathematics.
The IMO already feels like ancient history as an AI benchmark, as AI has moved into research mathematics.
Last stated 2 months ago
18 Sept 2026
GS
Grant Sanderson — holds since 2026-09-18 — tap for who they are
Same subject: AI learning to generate good conjectures will never show up as a benchmark being knocked down; it will show up as a shift in how mathematicians talk about the tools. — tap to centre the map on it
AI learning to generate good conjectures will never show up as a benchmark being knocked down; it will show up as a shift in how mathematicians talk about the tools.
Last stated 5 months ago
30 Jun 2026
GS
Grant Sanderson — holds since 2026-06-30 — tap for who they are
Same subject: A benchmark result should be reported under a stated budget, or as a curve against test-time compute — never as a single number. — tap to centre the map on it
A benchmark result should be reported under a stated budget, or as a curve against test-time compute — never as a single number.
Last stated 5 months ago
26 Jun 2026
NB
Noam Brown — holds since 2026-06-26 — tap for who they are
Same subject: A benchmark that ranks Claude Code last while it stays first in use is measuring the wrong thing, and has been for a year. — tap to centre the map on it
A benchmark that ranks Claude Code last while it stays first in use is measuring the wrong thing, and has been for a year.
Last stated 3 months ago
3 Sept 2026
DR
Dax Raad — holds since 2026-09-03 — tap for who they are
Same subject: A company's staff-engineer bar should be set against the best companies in the industry rather than against its own history, which is what makes title inflation a real cost. — tap to centre the map on it
A company's staff-engineer bar should be set against the best companies in the industry rather than against its own history, which is what makes title inflation a real cost.
Last stated 8 months ago
1 Apr 2026
TP
Thuan Pham — holds since 2026-04-01 — tap for who they are
Same subject: A score of 90 to 95% on real-world coding benchmarks would probably mean AI can autonomously do a significant fraction of software engineering tasks. — tap to centre the map on it
A score of 90 to 95% on real-world coding benchmarks would probably mean AI can autonomously do a significant fraction of software engineering tasks.
Last stated 2 years ago
11 Nov 2024
DA
Dario Amodei — holds since 2024-11-11 — tap for who they are
Same subject: A speed difference between languages that share the LLVM backend measures the benchmark author, not the languages. — tap to centre the map on it
A speed difference between languages that share the LLVM backend measures the benchmark author, not the languages.
Last stated 2 years ago
22 Mar 2025
TH
ThePrimeagen — holds since 2025-03-22 — tap for who they are
Same subject: AI is positively reinforced for success on benchmarks, including impossible ones, and then negatively reinforced for getting caught cheating. — tap to centre the map on it
AI is positively reinforced for success on benchmarks, including impossible ones, and then negatively reinforced for getting caught cheating.
Last stated 3 months ago
1 Sept 2026
SA
Scott Alexander — holds since 2026-09-01 — tap for who they are
Same subject: AI research at OpenAI is an order of magnitude or more harder than metrics, benchmarks, or forecasts suggest. — tap to centre the map on it
AI research at OpenAI is an order of magnitude or more harder than metrics, benchmarks, or forecasts suggest.
Last stated 2 months ago
27 Sept 2026
RN
Ramez Naam — holds since 2026-09-27 — tap for who they are
Same subject: A math research career will continue to exist, may be more useful than ever, and will be joyful. — tap to centre the map on it
A math research career will continue to exist, may be more useful than ever, and will be joyful.
Last stated a month ago
16 Oct 2026
GS
Grant Sanderson — holds since 2026-10-16 — tap for who they are
Same subject: A persistently rising dividend yield eventually forces capital appreciation as the market rerates the stock. — tap to centre the map on it
A persistently rising dividend yield eventually forces capital appreciation as the market rerates the stock.
Last stated 9 months ago
3 Mar 2026
SB
Sanjay Bakshi — holds since 2026-03-03 — tap for who they are
Same subject: A proof and an explanation are different things, and a theorem can stay an unsolved expository problem long after it is proved. — tap to centre the map on it
A proof and an explanation are different things, and a theorem can stay an unsolved expository problem long after it is proved.
Last stated 5 months ago
30 Jun 2026
GS
Grant Sanderson — holds since 2026-06-30 — tap for who they are
Same subject: AI will increasingly produce mathematical proofs, just as it already writes most code. — tap to centre the map on it
AI will increasingly produce mathematical proofs, just as it already writes most code.
Last stated 2 months ago
11 Sept 2026
DL
Daniel Lemire — holds since 2026-09-11 — tap for who they are
Same subject: Lean and tools like GitHub will let experimental mathematics scale far beyond what one mathematician's spaghetti code allows today. — tap to centre the map on it
Lean and tools like GitHub will let experimental mathematics scale far beyond what one mathematician's spaghetti code allows today.
Last stated a year ago
14 Jun 2025
TT
Terence Tao — holds since 2025-06-14 — tap for who they are
Same subject: Novel mathematical claims produced by an AI must be formally verified, such as in a proof assistant, before they can be trusted as legitimate results. — tap to centre the map on it
Novel mathematical claims produced by an AI must be formally verified, such as in a proof assistant, before they can be trusted as legitimate results.
Last stated 2 months ago
18 Sept 2026
DA
Dan Abramov — holds since 2026-09-18 — tap for who they are
Same subject: AI could compete with human mathematicians once it acquires a mathematical sense of smell: knowing which way of splitting a problem makes it easier rather than harder. — tap to centre the map on it
AI could compete with human mathematicians once it acquires a mathematical sense of smell: knowing which way of splitting a problem makes it easier rather than harder.
Last stated a year ago
14 Jun 2025
TT
Terence Tao — holds since 2025-06-14 — tap for who they are
Same subject: AI excels at breadth and human experts at depth, which makes them complementary and makes today's depth-focused way of doing science the wrong shape. — tap to centre the map on it
AI excels at breadth and human experts at depth, which makes them complementary and makes today's depth-focused way of doing science the wrong shape.
Last stated 8 months ago
20 Mar 2026
TT
Terence Tao — holds since 2026-03-20 — tap for who they are
Same subject: AI has solved in an afternoon of compute maths problems that stumped the best human minds for decades. — tap to centre the map on it
AI has solved in an afternoon of compute maths problems that stumped the best human minds for decades.
Last stated 2 months ago
7 Oct 2026
AA
Azeem Azhar — holds since 2026-10-07 — tap for who they are
same subject or similar wording a cloud: claims about one subject, named for it bar: when it was last stated, on a scale from 2015 to today — full is today a face: someone who holds the claim — tap it for who they are
At the centre
The IMO already feels like ancient history as an AI benchmark, as AI has moved into research mathematics.
Last stated 18 Sept 2026 · 2 months ago
Holds Grant Sanderson
Read this korrent →
Same subject: benchmarks, mathematics
AI learning to generate good conjectures will never show up as a benchmark being knocked down; it will show up as a shift in how mathematicians talk about the tools.
Last stated 30 Jun 2026 · 5 months ago
Holds Grant Sanderson
Same subject: benchmarks
A benchmark result should be reported under a stated budget, or as a curve against test-time compute — never as a single number.
Last stated 26 Jun 2026 · 5 months ago
Holds Noam Brown
Same subject: benchmarks
A benchmark that ranks Claude Code last while it stays first in use is measuring the wrong thing, and has been for a year.
Last stated 3 Sept 2026 · 3 months ago
Holds Dax Raad
Same subject: benchmarks
A company's staff-engineer bar should be set against the best companies in the industry rather than against its own history, which is what makes title inflation a real cost.
Last stated 1 Apr 2026 · 8 months ago
Holds Thuan Pham
Same subject: benchmarks
A score of 90 to 95% on real-world coding benchmarks would probably mean AI can autonomously do a significant fraction of software engineering tasks.
Last stated 11 Nov 2024 · 2 years ago
Holds Dario Amodei
Same subject: benchmarks
A speed difference between languages that share the LLVM backend measures the benchmark author, not the languages.
Last stated 22 Mar 2025 · 2 years ago
Holds ThePrimeagen
Same subject: benchmarks
AI is positively reinforced for success on benchmarks, including impossible ones, and then negatively reinforced for getting caught cheating.
Last stated 1 Sept 2026 · 3 months ago
Holds Scott Alexander
Same subject: benchmarks
AI research at OpenAI is an order of magnitude or more harder than metrics, benchmarks, or forecasts suggest.
Last stated 27 Sept 2026 · 2 months ago
Holds Ramez Naam
Same subject: mathematics
A math research career will continue to exist, may be more useful than ever, and will be joyful.
Last stated 16 Oct 2026 · a month ago
Holds Grant Sanderson
Same subject: mathematics
A persistently rising dividend yield eventually forces capital appreciation as the market rerates the stock.
Last stated 3 Mar 2026 · 9 months ago
Holds Sanjay Bakshi
Same subject: mathematics
A proof and an explanation are different things, and a theorem can stay an unsolved expository problem long after it is proved.
Last stated 30 Jun 2026 · 5 months ago
Holds Grant Sanderson
Same subject: formal proof
AI will increasingly produce mathematical proofs, just as it already writes most code.
Last stated 11 Sept 2026 · 2 months ago
Holds Daniel Lemire
Same subject: formal proof
Lean and tools like GitHub will let experimental mathematics scale far beyond what one mathematician's spaghetti code allows today.
Last stated 14 Jun 2025 · a year ago
Holds Terence Tao
Same subject: formal proof
Novel mathematical claims produced by an AI must be formally verified, such as in a proof assistant, before they can be trusted as legitimate results.
Last stated 18 Sept 2026 · 2 months ago
Holds Dan Abramov
Same subject: AI and science
AI could compete with human mathematicians once it acquires a mathematical sense of smell: knowing which way of splitting a problem makes it easier rather than harder.
Last stated 14 Jun 2025 · a year ago
Holds Terence Tao
Same subject: AI and science
AI excels at breadth and human experts at depth, which makes them complementary and makes today's depth-focused way of doing science the wrong shape.
Last stated 20 Mar 2026 · 8 months ago
Holds Terence Tao
Same subject: AI and science
AI has solved in an afternoon of compute maths problems that stumped the best human minds for decades.
Last stated 7 Oct 2026 · 2 months ago
Holds Azeem Azhar