rllingho

@DensaLabs

[rllingho @rllingho]

We just released Benchmark Registry: an open-source public reference service that gathers scattered AI benchmark results into one place.

https://t.co/mVvAMRV9YT

[rllingho @rllingho]

@1kartikkabadi1 Cant you just go to login items & extensions

[rllingho @rllingho]

@krishhgg How is this different from amphetamine?

[hayden @haydendevs]

i switched all my screens to light mode about a month ago and im noticeably happier and less tired

[rllingho @rllingho]

Haiku 5.5 now on Benchmark Registry!

CursorBench 4.0 (max): 48.4%
Terminal-Bench 4.0 (max): 39.2%
HLE Full (with tools, max): 57.4%

https://t.co/4QGB0ORfp1

[rllingho @rllingho]

Haiku 5.5 now on Benchmark Registry!

CursorBench 4.0 (max): 48.4%
Terminal-Bench 4.0 (max): 39.2%
HLE Full (with tools, max): 57.4%

https://t.co/4QGB0ORfp1

[Densa Labs @DensaLabs]

We have just added 1,872 new results to Benchmark Registry!

Most models now have 10+ results and the Compare feature now has more results to compare from.

https://t.co/kd8b36f0iC

[rllingho @rllingho]

Live:
https://t.co/mVvAMRV9YT

[rllingho @rllingho]

We just added 1,872 new results to Benchmark Registry!

The compare models feature now has more results to compare models to!

See the difference:

[rllingho @rllingho]

Live:
https://t.co/mVvAMRV9YT

[rllingho @rllingho]

We just added 1,872 new results to Benchmark Registry!

The compare models feature now has more results to compare models to!

See the difference:

[rllingho @rllingho]

Remember when everyone called Astra AGI

[rllingho @rllingho]

@mightyking The hell is that image

[rllingho @rllingho]

@deeponailabs https://t.co/OegKkCfZOh
:)

[rllingho @rllingho]

@yog_codes Neither. It uses the agents' own hooks. Claude Code, Codex etc. fire a Stop event when a turn ends (the session keeps running), plus events for approval prompts and rate-limit failures :)

[rllingho @rllingho]

@matt__makes Thanks!

[rllingho @rllingho]

@mitansh_j07 Thank you!

[rllingho @rllingho]

Benchmark results are currently scattered across blogs, model cards, reports, etc.

Benchmark Registry puts them in one place.

[rllingho @rllingho]

Benchmark results are currently scattered across blogs, model cards, reports, etc.

Benchmark Registry puts them in one place.

[rllingho @rllingho]

Benchmark Registry: One place for AI benchmark results.

95 models, 84 benchmarks, 942 results.

https://t.co/mVvAMRV9YT

[rllingho @rllingho]

Benchmark Registry: One place for AI benchmark results.

95 models, 84 benchmarks, 942 results.

https://t.co/mVvAMRV9YT

[rllingho @rllingho]

@yog_codes Neither. It uses the agents' own hooks. Claude Code, Codex etc. fire a Stop event when a turn ends (the session keeps running), plus events for approval prompts and rate-limit failures :)