Reposted by Latent.Space
Did you listen to the @latentspacepod.bsky.social podcast with lindy.ai creator ? He talks about this and how having the control flow not be an llm improves accuracy and makes them usable for a lot of tasks otherwise very complicated to describe solely with prompts.
November 20, 2024 at 2:21 PM
Did you listen to the @latentspacepod.bsky.social podcast with lindy.ai creator ? He talks about this and how having the control flow not be an llm improves accuracy and makes them usable for a lot of tasks otherwise very complicated to describe solely with prompts.
Reposted by Latent.Space
@latentspacepod.bsky.social highest signal by far
November 29, 2024 at 5:44 PM
@latentspacepod.bsky.social highest signal by far
Reposted by Latent.Space
If interested in the topic, I recommend listening to the
@latentspacepod.bsky.social podcast with Erik Shultz from Anthropic as the guest. Erik was heavily involved (led?) in achieving the leap in the SWE-bench score.
www.latent.space/p/claude-son...
@latentspacepod.bsky.social podcast with Erik Shultz from Anthropic as the guest. Erik was heavily involved (led?) in achieving the leap in the SWE-bench score.
www.latent.space/p/claude-son...
The new Claude 3.5 Sonnet, Computer Use, and Building SOTA Agents — with Erik Schluntz, Anthropic
Anthropic recently scored a huge win on OpenAI's turf by achieving SOTA on -their- SWE-Bench Verified benchmark, using an upgraded Claude 3.5 Sonnet. For the first time, they spill the beans.
www.latent.space
December 2, 2024 at 2:00 PM
If interested in the topic, I recommend listening to the
@latentspacepod.bsky.social podcast with Erik Shultz from Anthropic as the guest. Erik was heavily involved (led?) in achieving the leap in the SWE-bench score.
www.latent.space/p/claude-son...
@latentspacepod.bsky.social podcast with Erik Shultz from Anthropic as the guest. Erik was heavily involved (led?) in achieving the leap in the SWE-bench score.
www.latent.space/p/claude-son...