Matt (@unigram) header
Matt (@unigram) profile picture

'scientist' https://xitter.gq/t.co/PwxpV4LRL7

East Midlands
Joined June 2007
Photo by Matt (@unigram)Photo by Matt (@unigram)Photo by Matt (@unigram)Photo by Matt (@unigram)Photo by Matt (@unigram)Photo by Matt (@unigram)Photo by Matt (@unigram)Photo by Matt (@unigram)Photo by Matt (@unigram)Photo by Matt (@unigram)
Replying to @unigram
Perfect babies
3
Came across this plate / bumper sticker combo in NYC recently lol
169
2,887
127
108,808
2,536,112
Matt retweeted
hey @macklemore im sorry i tweeted in 2014 you should mackle less. you can mackle as much as you want. free palestine ✊🏽
284
41,488
395
512,205
4,215,101
just saw a tiktok that said 'pov you just found a hidden cafe inside a bookshop in cambridge' and it's the Waterstones cafe inside Waterstones.
59
1,297
102
40,219
427,731
guy on the street hollered "you got some nice legs" at me, so i looked back to give him the evil eye. it turned out to be a man in a wheelchair with no legs, and he said, "you never appreciate them untill their gone." Confused, i just said "i hear that" and kept walking.
127
2,233
58
102,485
1,279,505
things can only get better
8
1
36
5,783
Matt retweeted
One time my coworker put a 6 pan of c'ptn crunch and a 6 pan of milk on the dinner salad bar. We had to refill it like 6 times befor our chef found it and made us pull them.
35
533
5
25,030
767,127
Andy Burnham has Thunderbirds hair, David Miliband looks like Daria's stressed History teacher.
Matt retweeted
not even funny how some Americans talk with such authority and confidence on a sport they’re watching for the first time. it’s like me watching my first Rugby Union match and wanting piss-drinking to be banned
4
58
1
1,755
33,985
Don’t tell me about typos.
behind every published book is a typo that made it through 1.5 million rounds of edits
664
3,168
197
75,933
2,330,607
[average cbt enjoyer when i'm 2 hours late to meet them at the pub]: he probably has adhd. that he managed to overcome his executive function and time blindness enough to even show up at all is a sign he cares. should be grateful [me]: i'm da king of da playing football manager
11
189
5
2,556
51,769
In two to three years time, when Starmer and his government are no doubt deeply unpopular, I hope we in the media will ask ourselves: "Why were we so supine during the long 2024 election; why didn't we hold Labour properly to account while we could, and ask more probing questions, and explore their records, rather than give them such an easy ride?".
2,768
4,410
788
14,988
2,877,280
Sir Keir has played a blinder.
30
137
1,748
91,377
Keir Starmer has resigned
528
5,456
1,532
14,543
Soccer I love when they hold up the sign and a brand new beautiful boy takes the place of a dirty sweaty ruined one
59
8,103
293
75,158
I ran a script to replace every instance of 'whale' in Moby Dick with the word 'lesbian', and I have to tell you, Captain Ahab does not come out of it well
Replying to @ZackPolanski
Replace "billionaire" with "Jewish" in all Polanski's polemic and propaganda, and his antisemitism becomes clear. It's all just Zackshit.
51
2,391
24
44,923
654,869
You have secured funding from a Chinese state industrial bank to launch a new battery factory, but the catch is you may never leave the special economic zone where your plant is located. Which special economic zone do you choose?
6
4
35
4,875
Was not prepared for that follow up info or who it was the kid was printing out pictures of lmao
21
199
27
3,516
139,940
oomf urgently called to inform us that his friend ate shit biking on the west side highway bike path and a man helped him up + asked if he was ok and when he looked up it was none other than mayor zohran mamdani on his citibike. closest you can get irl to being saved by spiderman
99
8,203
103
166,610
1,363,738
This is just like being alive in the 1600s when they got good at making complicated clocks and deduced that every complicated thing in the universe probably functioned exactly like a clock
There's a quadrillion-dollar question at the heart of AI: Why are humans so much more sample efficient compared to LLM? There are three possible answers: 1. Architecture and hyperparameters (aka transformer vs whatever ‘algo’ cortical columns are implementing) 2. Learning rule (backprop vs whatever brain is doing) 3. Reward function @AdamMarblestone believes the answer is the reward function. ML likes to use pretty simple loss functions, like cross-entropy. These are easy to work with. But they might be too simple for sample-efficient learning. Adam thinks that, in humans, the large number of highly specialised cells in the ‘lizard brain’ might actually be encoding information for sophisticated loss functions, used for ‘training’ in the more sophisticated areas like the cortex and amygdala. Like: the human genome is barely 3 gigabytes (compare that to the TBs of parameters that encode frontier LLM weights). So how can it include all the information necessary to build highly intelligent learners? Well, if the key to sample-efficient learning resides in the loss function, even very complicated loss functions can still be expressed in a couple hundred lines of Python code.
102
952
32
12,544
833,036