41. @ @NirDiamantAI Peter Steinberger told me that he wants PR to be "prompt request". His agents are perf... @NirDiamantAI Peter Steinberger told me that he wants PR to be "prompt request". His agents are perfectly capable of implementing most ideas, so there is no need to take your idea, 04/05 00:54 ♡
42. Wow, this tweet went very viral! I wanted share a possibly slightly improved version of the tweet i... Wow, this tweet went very viral! I wanted share a possibly slightly improved version of the tweet in an "idea file". The idea of the idea file is that in this era of LLM agents, th 04/05 00:45 ♡
43. O Oh and in the natural extrapolation, you could imagine that every question to a frontier grade LLM s... Oh and in the natural extrapolation, you could imagine that every question to a frontier grade LLM spawns a team of LLMs to automate the whole thing: iteratively construct an entir 04/03 04:54 ♡
44. L LLM Knowledge Bases Something I'm finding very useful recently: using LLMs to build personal knowle... LLM Knowledge Bases Something I'm finding very useful recently: using LLMs to build personal knowledge bases for various topics of research interest. In this way, a large fract 04/03 04:42 ♡
45. @ @gvanrossum LLM = CPU (data: tokens not bytes, dynamics: statistical and vague not deterministic and... @gvanrossum LLM = CPU (data: tokens not bytes, dynamics: statistical and vague not deterministic and precise) Agent = operating system kernel 💬 154 🔄 328 ❤️ 4837 &# 04/01 02:59 ♡
46. N New supply chain attack this time for npm axios, the most popular HTTP client library with 300M week... New supply chain attack this time for npm axios, the most popular HTTP client library with 300M weekly downloads. Scanning my system I found a use imported from googleworkspace/cli 03/31 13:23 ♡
47. - - Drafted a blog post - Used an LLM to meticulously improve the argument over 4 hours. - Wow, feelin... - Drafted a blog post - Used an LLM to meticulously improve the argument over 4 hours. - Wow, feeling great, it’s so convincing! - Fun idea let’s ask it to argue the opposite. - LL 03/28 23:56 ♡
48. When I built menugen ~1 year ago, I observed that the hardest part by far was not the code itself, i... When I built menugen ~1 year ago, I observed that the hardest part by far was not the code itself, it was the plethora of services you have to assemble like IKEA furniture to make 03/27 00:10 ♡
49. ( (I cycle through all LLMs over time and all of them seem to do this so it's not any particular imple... (I cycle through all LLMs over time and all of them seem to do this so it's not any particular implementation but something deeper, e.g. maybe during training, a lot of the inf 03/26 00:22 ♡
50. O One common issue with personalization in all LLMs is how distracting memory seems to be for the mode... One common issue with personalization in all LLMs is how distracting memory seems to be for the models. A single question from 2 months ago about some topic can keep coming up as s 03/26 00:05 ♡
