By: The Posts Author | Posted on: 4 Apr 23
[just a few live tickets left] Let’s debate at MIT! Free! On Tuesday, April 4, 2023, at MIT’s Wong Auditorium (E51-115) a modified Oxford Union-style debate will be held to debate DEI programs. REGISTRATION IS REQUIRED: sloangroups.mit.edu/adamsmit… LIVESTREAM OPTION:… twitter.com/i/web/status/164…
[just a few live tickets left] Let’s debate at MIT! Free! On Tuesday, April 4, 2023, at MIT’s Wong Auditorium (E51-115) a modified Oxford Union-style debate will be held to debate DEI programs. REGISTRATION IS REQUIRED: sloangroups.mit.edu/adamsmit… LIVESTREAM OPTION:… twitter.com/i/web/status/164…
By: The Posts Author | Posted on: 4 Apr 23
Got access to Claude today (an older invite expired unused, alas) . On my test question it hallucinated much worse that GPT3.5 about on par with Bard, 9 wrong out of 10: Who are the 10 most prominent guests on the Jim Rutt Show podcast? 📷 Here are the 10 most prominent… Quoted feed from @jim_rutt 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: twitter.com/i/web/status/164…
Got access to Claude today (an older invite expired unused, alas) . On my test question it hallucinated much worse that GPT3.5 about on par with Bard, 9 wrong out of 10: Who are the 10 most prominent guests on the Jim Rutt Show podcast? 📷 Here are the 10 most prominent… Quoted feed from @jim_rutt Got access to Bard.
By: The Posts Author | Posted on: 4 Apr 23
There are differing short termism memories: working memory for from a second to 100 seconds. there are two working memories (at least) on auditory, the other for images. There is also a short term episodic memory of about 5 minutes that holds considerable detail on what you… twitter.com/i/web/status/164…
There are differing short termism memories: working memory for from a second to 100 seconds. there are two working memories (at least) on auditory, the other for images. There is also a short term episodic memory of about 5 minutes that holds considerable detail on what you… twitter.com/i/web/status/164…
By: The Posts Author | Posted on: 4 Apr 23
Who did Trump’s alleged crime harm? It appears to be a purely technical violation.
Who did Trump’s alleged crime harm? It appears to be a purely technical violation.
By: The Posts Author | Posted on: 4 Apr 23
Yo, entrepreneurs. Do this. ⬇️⬇️⬇️ Quoted feed from @jim_rutt 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…
Yo, entrepreneurs. Do this. ⬇️⬇️⬇️ Quoted feed from @jim_rutt 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…
By: The Posts Author | Posted on: 4 Apr 23
o course we don’t know it actually works in animals either.
o course we don’t know it actually works in animals either.
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…