Lol their page finally loaded. They added an example scenario of "Filling in Form 1040" - which made me laugh out loud. That is indeed something most US citizens cannot accurately do even with expensive proprietary tax…
Back in the day, the sentiment was the MySQL was more-performant but the criticized tradeoff of having "cut corners". I still remember when their transaction support InnoDB table engine came out. Anyway Postgres was…
"There's no such thing as public opinion, merely published opinion". While on the one hand we should never discount the impact of incompetence, gross negligence, or deliberate mismanagement there's a reason this story…
There's also https://github.com/code-yeongyu/oh-my-openagent which is very active
This just in: fallible Humans (un)knowingly produce unreliable data. LLM training on unreliable data impacts accuracy. Some sources of Human-produced data are measurably more reliable than others. "Trust the science!"
National pride aside, we must decide if competition is good or is it bad. In the west we've been conditioned that competition is good and expect consequences and tradeoffs. In this case we're seeing incumbents trying to…
As with many others among these threads I don't see how the timing works out for K3 to have trained on distilled Fable usage. There should be at least a tacit academic acknowledgment of Kimi's own design efforts.…
There's this https://github.com/code-yeongyu/oh-my-openagent which implements the OP article's oracle pattern across 11 roles. Each role has a whole ranking of recommended LLMs across many providers. For example…
Lol their page finally loaded. They added an example scenario of "Filling in Form 1040" - which made me laugh out loud. That is indeed something most US citizens cannot accurately do even with expensive proprietary tax…
Back in the day, the sentiment was the MySQL was more-performant but the criticized tradeoff of having "cut corners". I still remember when their transaction support InnoDB table engine came out. Anyway Postgres was…
"There's no such thing as public opinion, merely published opinion". While on the one hand we should never discount the impact of incompetence, gross negligence, or deliberate mismanagement there's a reason this story…
There's also https://github.com/code-yeongyu/oh-my-openagent which is very active
This just in: fallible Humans (un)knowingly produce unreliable data. LLM training on unreliable data impacts accuracy. Some sources of Human-produced data are measurably more reliable than others. "Trust the science!"
National pride aside, we must decide if competition is good or is it bad. In the west we've been conditioned that competition is good and expect consequences and tradeoffs. In this case we're seeing incumbents trying to…
As with many others among these threads I don't see how the timing works out for K3 to have trained on distilled Fable usage. There should be at least a tacit academic acknowledgment of Kimi's own design efforts.…
There's this https://github.com/code-yeongyu/oh-my-openagent which implements the OP article's oracle pattern across 11 roles. Each role has a whole ranking of recommended LLMs across many providers. For example…