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: 4 Apr 23
Personally, I detest Trump, and have a strong prejudice against people anything like Trump. I also believe on object grounds that he is a person completely unfit for any electoral office. So I suppose at that level I might have a bit of TDS. However, I also believe strongly… twitter.com/i/web/status/164…
Personally, I detest Trump, and have a strong prejudice against people anything like Trump. I also believe on object grounds that he is a person completely unfit for any electoral office. So I suppose at that level I might have a bit of TDS. However, I also believe strongly… twitter.com/i/web/status/164…
By: The Posts Author | Posted on: 4 Apr 23
actually why it may fly: the main barrier to FPGAing many algorithms is that it takes too much human brainpower and time. If AIs could do that behind the scenes then it could be Standard Operating Procedure. BTW, I’m not imagining always implementing the entire algorithms at… twitter.com/i/web/status/164…
actually why it may fly: the main barrier to FPGAing many algorithms is that it takes too much human brainpower and time. If AIs could do that behind the scenes then it could be Standard Operating Procedure. BTW, I’m not imagining always implementing the entire algorithms at… twitter.com/i/web/status/164…
By: The Posts Author | Posted on: 4 Apr 23
The question one might ask is: “would this action have resulted in the prosecution of someone of the opposite political party for a similar offense?”. In Georgia the Attorney General is a Republican, which should boost our confidence at least some that any prosecution isn’t… twitter.com/i/web/status/164…
The question one might ask is: “would this action have resulted in the prosecution of someone of the opposite political party for a similar offense?”. In Georgia the Attorney General is a Republican, which should boost our confidence at least some that any prosecution isn’t… twitter.com/i/web/status/164…
By: The Posts Author | Posted on: 4 Apr 23
The Trump prosecution in NY continues to bother me. The reality is that in our current Utopia of Rules essentially ALL of us are guilty of something. The more complicated a life you lead the more likely you are to be entangled in some Malum Prohibitum infraction.… twitter.com/i/web/status/164…
The Trump prosecution in NY continues to bother me. The reality is that in our current Utopia of Rules essentially ALL of us are guilty of something. The more complicated a life you lead the more likely you are to be entangled in some Malum Prohibitum infraction.… twitter.com/i/web/status/164…
By: The Posts Author | Posted on: 4 Apr 23
hmmmm. very interesting
hmmmm. very interesting
By: The Posts Author | Posted on: 4 Apr 23
Interesting chat today with @C4COMPUTATION about the possibility of LLMs being able to automate more deeply into the tech-stack in ways that are generally not cost-effective for humans. What if we had LLMs that could quickly and cheaply custom program FPGAs and/or GPUs for our… twitter.com/i/web/status/164…
Interesting chat today with @C4COMPUTATION about the possibility of LLMs being able to automate more deeply into the tech-stack in ways that are generally not cost-effective for humans. What if we had LLMs that could quickly and cheaply custom program FPGAs and/or GPUs for our… twitter.com/i/web/status/164…