By: The Posts Author | Posted on: 4 Apr 23
anybody tried GPTs on Haskell or F#?
anybody tried GPTs on Haskell or F#?
By: The Posts Author | Posted on: 4 Apr 23
One could exapt off the computer language capacity by defining APIs that provide real world affordances and real world telemetry. Has anyone tried “educating” an LLM about a new API via fine tuning or using the context window? I haven’t dug into it but that sounds a lot… Quoted feed from @jim_rutt So we already know that GPT3.5 and above are damn good at high level language computer programming (Python, C, SQL etc) . What other affordances might LLMs be able to compositionally orchestrate?
One could exapt off the computer language capacity by defining APIs that provide real world affordances and real world telemetry. Has anyone tried “educating” an LLM about a new API via fine tuning or using the context window? I haven’t dug into it but that sounds a lot… Quoted feed from @jim_rutt So we already know that GPT3.5 and above
By: The Posts Author | Posted on: 2 Apr 23
Anybody know of a Windows equivalent to Rewind? https://t.co/qm1RjbjmHh. Hooking it up to a latent semantic space vector index and GPT-4 would be da bombe.
Anybody know of a Windows equivalent to Rewind? https://t.co/qm1RjbjmHh. Hooking it up to a latent semantic space vector index and GPT-4 would be da bombe.
By: The Posts Author | Posted on: 2 Apr 23
Jim Rutt retweeted: “I have one consistency, which is being against the totalitarian – on the left and on the right. The totalitarian, to me, is the enemy; the one that’s absolute, the one that wants control over the inside of your head, not just your actions and your taxes.”
Jim Rutt retweeted: “I have one consistency, which is being against the totalitarian – on the left and on the right. The totalitarian, to me, is the enemy; the one that’s absolute, the one that wants control over the inside of your head, not just your actions and your taxes.”
By: The Posts Author | Posted on: 2 Apr 23
Anybody know of a Windows equivalent to Rewind? https://t.co/qm1RjbjmHh. Hooking it up to a latent space vector index and GPT-4 would be da bombe.
Anybody know of a Windows equivalent to Rewind? https://t.co/qm1RjbjmHh. Hooking it up to a latent space vector index and GPT-4 would be da bombe.
By: The Posts Author | Posted on: 2 Apr 23
@indy_johar And the nature of the dynamics is what distinguishes effective orgs from ineffective ones. Ignore those boxes and links, watch the dynamics!
@indy_johar And the nature of the dynamics is what distinguishes effective orgs from ineffective ones. Ignore those boxes and links, watch the dynamics!
By: The Posts Author | Posted on: 2 Apr 23
Jim Rutt retweeted: The amount of money given out during COVID was so obscene that it took an orgy of consumer spending over three years to unload it. But the American consumer is relentless and will declare victory by spending the last of it in just a few months.
Jim Rutt retweeted: The amount of money given out during COVID was so obscene that it took an orgy of consumer spending over three years to unload it. But the American consumer is relentless and will declare victory by spending the last of it in just a few months.
By: The Posts Author | Posted on: 2 Apr 23
GPT-4. 9 out of 10 correct: Who are 10 prominent guests who have appeared on the Jim Rutt Show podcast? 1 / 1 As of my knowledge cutoff in September 2021, here are ten prominent guests who have appeared on the Jim Rutt Show podcast. The podcast features discussions on complex…
GPT-4. 9 out of 10 correct: Who are 10 prominent guests who have appeared on the Jim Rutt Show podcast? 1 / 1 As of my knowledge cutoff in September 2021, here are ten prominent guests who have appeared on the Jim Rutt Show podcast. The podcast features discussions on complex…
By: The Posts Author | Posted on: 2 Apr 23
Got access to Bard. On my test queries it hallucinates like crazy. Worse than GPT3.5. Way worse than GPT-4. And rather prolix with its hallucinating. For example: only one (Rushkoff) is real:
Got access to Bard. On my test queries it hallucinates like crazy. Worse than GPT3.5. Way worse than GPT-4. And rather prolix with its hallucinating. For example: only one (Rushkoff) is real:
By: The Posts Author | Posted on: 2 Apr 23
Twitter has released the code for its recommendation algorithms. Anybody taken a look yet? https://t.co/I9X9qdRqpb
Twitter has released the code for its recommendation algorithms. Anybody taken a look yet? https://t.co/I9X9qdRqpb