The 5000 series benchmarks…
January 8, 2025 at 2:29 PM
The 5000 series benchmarks…
Rapidly rebranding all my search benchmarks as eval awareness benchmarks
March 6, 2026 at 7:33 PM
Rapidly rebranding all my search benchmarks as eval awareness benchmarks
we set new benchmarks every day here
Joking aside, what year of your life did you reach your absolute peak of being an insufferable shithead?
June 3, 2025 at 2:52 PM
we set new benchmarks every day here
finally, real benchmarks
www.assbench.com
www.assbench.com
LLM AssBench
LLM Benchmark - One prompt, Multiple models, Multiple dates
www.assbench.com
September 23, 2026 at 4:06 AM
finally, real benchmarks
www.assbench.com
www.assbench.com
Celebrating 1 year of making my BenchMarks and showing exceptional growth! Happy Christmas Eve! ❤️💚
#ThatsALotOfFoodAndSnacks
#Benchmarks
#DogsOfBlueSky
#ThatsALotOfFoodAndSnacks
#Benchmarks
#DogsOfBlueSky
December 25, 2024 at 12:20 AM
Celebrating 1 year of making my BenchMarks and showing exceptional growth! Happy Christmas Eve! ❤️💚
#ThatsALotOfFoodAndSnacks
#Benchmarks
#DogsOfBlueSky
#ThatsALotOfFoodAndSnacks
#Benchmarks
#DogsOfBlueSky
My eval guy told me models keep saturating his benchmarks so I asked how many benchmarks he has and he said he just goes to Artificial Analysis and gets a new benchmark afterwards so I said it sounds like he’s just feeding benchmarks to models and then François Chollet started crying.
September 3, 2026 at 8:51 PM
My eval guy told me models keep saturating his benchmarks so I asked how many benchmarks he has and he said he just goes to Artificial Analysis and gets a new benchmark afterwards so I said it sounds like he’s just feeding benchmarks to models and then François Chollet started crying.
Today we have published BioEmu-Benchmarks (MIT license): a code to evaluate the multi-conformation sampling benchmarks, MD free energy landscape benchmarks, and folding free energy benchmarks shown in the BioEmu-1 paper with BioEmu or your own model. Some details below 🧵
github.com/microsoft/bi...
github.com/microsoft/bi...
GitHub - microsoft/bioemu-benchmarks: Benchmarking code accompanying the release of `bioemu`
Benchmarking code accompanying the release of `bioemu` - microsoft/bioemu-benchmarks
github.com
February 21, 2025 at 3:49 PM
Today we have published BioEmu-Benchmarks (MIT license): a code to evaluate the multi-conformation sampling benchmarks, MD free energy landscape benchmarks, and folding free energy benchmarks shown in the BioEmu-1 paper with BioEmu or your own model. Some details below 🧵
github.com/microsoft/bi...
github.com/microsoft/bi...
AGI benchmarks are decoys
December 23, 2024 at 12:41 PM
AGI benchmarks are decoys
Crawford currently running ahead of her county-level benchmarks by about 3 points. That would indicate a close victory, if it holds. docs.google.com/spreadsheets...
Wisconsin 2024 POTUS/2025 SCOWI benchmarks
docs.google.com
April 2, 2025 at 1:25 AM
Crawford currently running ahead of her county-level benchmarks by about 3 points. That would indicate a close victory, if it holds. docs.google.com/spreadsheets...
Steam Machine review and benchmarks: www.youtube.com/watch?v=66Qz...
Valve Steam Machine Review: GPU & CPU Benchmarks, SteamOS Test, Thermals, Noise, and Price
YouTube video by Gamers Nexus
www.youtube.com
June 22, 2026 at 5:01 PM
Steam Machine review and benchmarks: www.youtube.com/watch?v=66Qz...
🇪🇺 EU confirms third payment to Ukraine under the Ukraine Facility program after Kyiv meets 13 reform benchmarks.
EU Council Confirms Third Ukraine Facility Payment as Kyiv Meets Reform Benchmarks
The European Council has confirmed the third tranche of funding for Ukraine, following its adherence to crucial reform benchmarks.
united24media.com
March 17, 2025 at 12:44 PM
🇪🇺 EU confirms third payment to Ukraine under the Ukraine Facility program after Kyiv meets 13 reform benchmarks.
Affirmative action lowers the benchmarks for American workers and should be abolished. Here’s why we’re loosening our ICE hiring standards yet again.
by Stephen Miller and Kristi Noem
by Stephen Miller and Kristi Noem
August 8, 2025 at 10:36 PM
Affirmative action lowers the benchmarks for American workers and should be abolished. Here’s why we’re loosening our ICE hiring standards yet again.
by Stephen Miller and Kristi Noem
by Stephen Miller and Kristi Noem
Very hard to find AI benchmarks that don't look like this
(and yes, that includes obscure benchmarks that nobody would train on and benchmarks with holdout datasets)
(and yes, that includes obscure benchmarks that nobody would train on and benchmarks with holdout datasets)
February 13, 2026 at 7:26 PM
Very hard to find AI benchmarks that don't look like this
(and yes, that includes obscure benchmarks that nobody would train on and benchmarks with holdout datasets)
(and yes, that includes obscure benchmarks that nobody would train on and benchmarks with holdout datasets)
things off the top of my head that i can think of that conservatives have called tyranny
- health care subsidies
- seeing pronouns in an email
- being suspended from a social media platform
- pride month
- baking a cake for a same sex wedding
- legal rulings against donald trump
- EV benchmarks
- health care subsidies
- seeing pronouns in an email
- being suspended from a social media platform
- pride month
- baking a cake for a same sex wedding
- legal rulings against donald trump
- EV benchmarks
Trump's thugs are going hog wild and tossing gas around in one of the busiest commercial districts in Minneapolis, just a mile or so from where I live. Complete insanity.
(vid via Ford Fischer on X)
(vid via Ford Fischer on X)
January 12, 2026 at 9:51 PM
things off the top of my head that i can think of that conservatives have called tyranny
- health care subsidies
- seeing pronouns in an email
- being suspended from a social media platform
- pride month
- baking a cake for a same sex wedding
- legal rulings against donald trump
- EV benchmarks
- health care subsidies
- seeing pronouns in an email
- being suspended from a social media platform
- pride month
- baking a cake for a same sex wedding
- legal rulings against donald trump
- EV benchmarks
Meta is so desperate to be seen as a leader in AI that it’s been caught cheating in AI benchmarks. Reminds me of the time Facebook artificially inflated its video views to con advertisers www.theverge.com/meta/645012/...
Meta got caught gaming AI benchmarks
Meta released Llama 4, but the announcement was eclipsed by benchmark drama.
www.theverge.com
April 8, 2025 at 1:48 AM
Meta is so desperate to be seen as a leader in AI that it’s been caught cheating in AI benchmarks. Reminds me of the time Facebook artificially inflated its video views to con advertisers www.theverge.com/meta/645012/...
This remains a very close race. But you'd rather be Talarico. For context and benchmarks, I believe (best recollection) only one poll ever showed Beto O'Rourke ahead in 2018. By two points and it was a clear outlier.
September 25, 2026 at 5:49 PM
This remains a very close race. But you'd rather be Talarico. For context and benchmarks, I believe (best recollection) only one poll ever showed Beto O'Rourke ahead in 2018. By two points and it was a clear outlier.
If Musk meets all the benchmarks of his new $1 trillion pay package from Tesla he will be paid $274 MILLION EVERY DAY FOR THE NEXT 10 YEARS
This is his part-time job
This is his part-time job
November 7, 2025 at 1:59 AM
If Musk meets all the benchmarks of his new $1 trillion pay package from Tesla he will be paid $274 MILLION EVERY DAY FOR THE NEXT 10 YEARS
This is his part-time job
This is his part-time job
An excellent piece. ProPublica one of the true benchmarks of principled public-interest journalism in our current moment.
"The Shadow President," @andykroll.bsky.social's deep dive into Russell Vought, has just won a George Polk award for political reporting.
The piece chronicles Vought’s rise from the Senate mailroom to his position as one of the most influential players in the Trump administration.
Read it here:
The piece chronicles Vought’s rise from the Senate mailroom to his position as one of the most influential players in the Trump administration.
Read it here:
Russell Vought, Trump’s Shadow President
From the wholesale gutting of federal agencies to the ongoing government shutdown, Russell Vought has drawn the road map for Trump’s second term. Vought has consolidated power to an extent that inside...
www.propublica.org
February 18, 2026 at 8:12 PM
An excellent piece. ProPublica one of the true benchmarks of principled public-interest journalism in our current moment.
opus 4.6 is a significant step up at my openscad benchmarks
February 5, 2026 at 7:54 PM
opus 4.6 is a significant step up at my openscad benchmarks
February 13, 2025 at 3:48 PM
Poor people always have a hard time. They don't call it poverty for kicks. Which is why you've gotta set standards & benchmarks if you're going to measure improvement short of ending poverty. Some folks mistake the benchmarks for the goal. Some folks discount the benchmarks. Can't do either.
just gonna speak for myself that a decoupling of economic sentiment and reality doesn’t mean that I don’t think poor people are having a hard time — my issue is that some thinktank moron writing in Politico had a weirdly easy time infiltrating the online left’s thought process
February 12, 2025 at 11:57 PM
Poor people always have a hard time. They don't call it poverty for kicks. Which is why you've gotta set standards & benchmarks if you're going to measure improvement short of ending poverty. Some folks mistake the benchmarks for the goal. Some folks discount the benchmarks. Can't do either.
this is what we in the biz like to call an "uh oh" www.theverge.com/meta/645012/...
April 8, 2025 at 1:41 AM
this is what we in the biz like to call an "uh oh" www.theverge.com/meta/645012/...
Meta got caught gaming AI benchmarks
Meta got caught gaming AI benchmarks
Meta released Llama 4, but the announcement was eclipsed by benchmark drama.
buff.ly
April 8, 2025 at 1:40 AM
Meta got caught gaming AI benchmarks
Meta??? Gaming a metric??? To make itself look good??? Impossible www.theverge.com/meta/645012/...
Meta got caught gaming AI benchmarks
Meta released Llama 4, but the announcement was eclipsed by benchmark drama.
www.theverge.com
April 8, 2025 at 2:45 AM
Meta??? Gaming a metric??? To make itself look good??? Impossible www.theverge.com/meta/645012/...