Grant Slatton @GrantSlatton Twitter profile

Last Seen Profiles

@tigerbachmeier

@AsimTanvir

@H_AmorinForge

@6hozKtJjfcQjcPL

@JaggerWolverine

@VinaRockOficial

@ScienceCareers

@gonzalezpons

@HammontreeEthan

@harucolacola

@CaliforniaOld

@Noorfatima01112

@apatrisilva

@extrimrace

@peytonpartyhorn

@yourseanm

@power_guido___

@acabusoficial

@JargonQuest

@mikaan525

@Anish91710850

@DR_BCW

@MathGiftedBlack

@MilkyPomuri

@tkv1us

@Divinedirtclod

@nutriOT

@stadt_halle

@RondRami

@Cos_Code

@haneol_R

@deruxx

@phototacticx

@Afc_Gabbyy

@THFC_cf

Grant Slatton

@GrantSlatton

5 months

We don't talk enough about how insane aluminum foil is Imagine telling some ancient person we have so much abundance in our time that we use very thin metal as a disposable paper-like wrapping and it costs essentially nothing

80

439

13K

Grant Slatton

@GrantSlatton

1 month

Wait so better reaction times are correlated to higher IQ?? How much of being smart is just your neurons firing faster? Can we just overclock this meat CPU?

612

523

10K

Grant Slatton

@GrantSlatton

24 days

My friend works for a large nonprofit They just received a $20K donation and are having a 110 person, 90 minute meeting discussing how they’re gonna spend it The total value of these 110 people’s 90 minutes is $10K

87

251

9K

Grant Slatton

@GrantSlatton

2 months

Had my American mind blown when visiting a friend in Germany There was a 300 year old building they'd gutted and put in a Burger King I said "Alex, this is awful! They turned this 300 year old building into a fast food place!" He said "Grant, it's *only* 300 years old"

83

195

7K

Grant Slatton

@GrantSlatton

3 months

Founder of Trader Joe's set up a bonus system where overperforming store managers are the highest compensated employees of the business — more than those at HQ He wanted to avoid any incentives for them to want to get into the bureaucracy Big tech companies should take note IMO

47

352

7K

Grant Slatton

@GrantSlatton

5 months

@SurrealistShip I’m doing what? Idk man I am just pressing random buttons really fast. It’s called wavedashing? Oh my guy, what’s his name, Falcrow? I’m shield tilting now? Really? Where do you come up with these crazy names haha. Oh wow, 20-0, this game is fun.

1

29

5K

Grant Slatton

@GrantSlatton

4 months

A couple years ago I started installing these dog bag dispensers on all the telephone poles around our house I restock them as we walk our dog, takes no time and maybe $20/yr of bags It's easy to add to the commons, just do it, nobody will stop you

43

238

4K

Grant Slatton

@GrantSlatton

4 months

There was a great line I couldn't quite remember from "One Hundred Years of Solitude" Search engines & ChatGPT couldn't recall it either from my bad description Wrote a little 20 line program to read the whole book and found it in a minute, cost 25 cents Wild times we live in

66

247

3K

Grant Slatton

@GrantSlatton

5 months

@_brendand_ I think it's interesting because they could *comprehend* it immediately -- they had metal foil back then, too (copper, gold, tin), it was just insanely expensive

2

6

3K

Grant Slatton

@GrantSlatton

3 months

A favorite load balancing technique at AWS is "the power of two random choices" On the left, nodes are chosen and used at random On the right, 2 nodes are chosen at random, but only the minimum is used This simple technique balances load very well

37

323

3K

Grant Slatton

@GrantSlatton

4 months

How it feels to hunt bugs with GPT4 at my side

25

121

2K

Grant Slatton

@GrantSlatton

4 months

The male-coded version of astrology is the guys who think they can see simple patterns in stock price graphs "Oh yeah that's a double-mountain followed by a head-and-shoulders, time to buy"

49

116

2K

Grant Slatton

@GrantSlatton

4 months

There's a lot of talent locked up in risk-averse FAANG staff engineers Weird to me more bigtechs don't offer in-house startup programs with these people "We'll pay salary and take equity, try your idea for a year, if it doesn't work, go back to your old job"

131

93

2K

Grant Slatton

@GrantSlatton

8 months

The new GPT model, gpt-3.5-turbo-instruct, can play chess around 1800 Elo. I had previously reported that GPT cannot play chess, but it appears this was just the RLHF'd chat models. The pure completion model succeeds. See game & thoughts below:

Grant Slatton

@GrantSlatton

8 months

GPT4 cannot play chess. Expected to get a bot up to ~1000 Elo and totally failed -- but negative results are still interesting! Even given verbose prompting, board state descriptions, CoT, etc, it loses badly to depth=1 engine. Code & notes below.

26

15

144

103

266

2K

Grant Slatton

@GrantSlatton

3 months

Imagine if Google had kept the invention of the transformer secret and released something like Gemini without the public having any idea how it worked

34

49

1K

Grant Slatton

@GrantSlatton

24 days

@zswitten Medical nonprofit, so it's the doctors and nurses and stuff who are in this meeting instead of seeing patients

5

3

1K

Grant Slatton

@GrantSlatton

4 months

It's weird to me more self-avowed communists don't set up actual communes It's actually really easy to mostly exit modern society and form your own parallel thing, just look at the Amish Farmland is like $3K/acre, easy to pool resources and form your own little town if you want

144

42

1K

Grant Slatton

@GrantSlatton

1 year

GPT can iteratively write, debug, and test programs to accomplish arbitrary goals. Pictured: GPT reading snippets of HTML from HN and building a headline scraper in Python, overcoming bugs by simply reading the errors and self-judgments and hypothesizing to itself. Thread ↓

24

167

1K

Grant Slatton

@GrantSlatton

4 months

Back in the 60s and 70s they were giving out CS PhDs for inventing algorithms used to solve leetcode mediums today We were born too late

16

70

1K

Grant Slatton

@GrantSlatton

4 months

I knew a kid in elementary school who would assign a daily ranking to other kids Some kids cared about the rankings, giving him status, which made more kids care about his rankings, and soon enough he was the highest status kid on the playground Child psychology is wild

28

37

986

Grant Slatton

@GrantSlatton

5 months

My most toxic belief is thinking I could turn a batch of highschool graduates into L5 FAANG engineers in about 2 years of full-time work One year to learn all the CS fundamentals, another year for software engineering University overrated, apprenticeship learning underrated

67

28

972

Grant Slatton

@GrantSlatton

2 months

For reference the church we had been in that same morning was 800 years old

0

3

874

Grant Slatton

@GrantSlatton

1 year

Added arbitrary context free grammar constraints to llama.cpp Can now plug in any llama.cpp compatible model and give an exact grammar spec: JSON, etc Excited to use with more powerful local models as they are released Thanks @ggerganov & friends for such a wonderful project.

32

91

823

Grant Slatton

@GrantSlatton

1 year

Don't let anyone tell you GPT can't do math -- you just have to send it to elementary school first.

19

60

805

Grant Slatton

@GrantSlatton

1 year

GPT can use a web browser to answer questions. When embedded in a REPL environment and prompted to strategize and monologue, agent-like behavior emerges. The agent can solve multi-step problems that involve going to pages, following links, reading the next page, etc. Thread ↓

26

97

765

Grant Slatton

@GrantSlatton

2 months

@var_epsilon The responses are definitely ChatGPT right??

9

1

650

Grant Slatton

@GrantSlatton

4 months

My all-time favorite datastructures & algorithms interview question: Design a key-value datastructure with methods: insert, delete, and getRandom All methods must be faster than O(N) There are at least 3 solutions, and it's a real problem I actually had to solve at work

42

24

618

Grant Slatton

@GrantSlatton

1 month

@pastaraspberry the 20ms guy

8

0

601

Grant Slatton

@GrantSlatton

5 months

Python won because you can download IDLE, type print("Hello world") and you're now a programmer As a kid, I tried to "download C++" What's GCC? What's a linker? How to point my IDE to it? As a kid, you don't even know what words to google. So Python it was

78

17

593

Grant Slatton

@GrantSlatton

5 months

A year ago we spent Christmas in the hospital as my wife had a serious health issue Doctors misdiagnosed and mistreated her for weeks, but eventually a specialist figured it out Months later, GPT4 came out and correctly diagnosed given only the notes from the first doctor

21

39

579

Grant Slatton

@GrantSlatton

2 months

I'm still open to the idea that all LLMs can do is interpolate, but that we also don't have a good grasp on what it even means to interpolate between concepts in billion dimensional space Maybe all the ideas we could ever have are already inside the convex hull of existing ideas

68

42

578

Grant Slatton

@GrantSlatton

4 months

@DanielParker_13 We need to start commonsmaxxing

6

29

575

Grant Slatton

@GrantSlatton

1 month

My favorite way to think about this is with space-filling curves For example, the picture shows a 1D line is able to encode 3D coordinates If you train an autoencoder to do this and visualize the output it will look roughly like this

Dwarkesh Patel

@dwarkesh_sp

1 month

It’s wild that models encode more features (things like random street names, people, concepts, etc) than they have parameters. But a parameter is just a single number. How is this even possible? @TrentonBricken and @_sholtodouglas on superposition:

24

32

387

14

42

576

Grant Slatton

@GrantSlatton

24 days

@_nmilo It’s a medical nonprofit so this corresponds to patients the medical staff isn’t seeing while they attend the meeting which directly translates to revenue

5

3

521

Grant Slatton

@GrantSlatton

2 months

@JCorvinusVR This video also has some obvious non-euclidean moments

Tim Brooks

@_tim_brooks

2 months

"fly through tour of a museum with many paintings and sculptures and beautiful works of art in all styles" Video generated by #Sora

314

592

3K

9

10

475

Grant Slatton

@GrantSlatton

2 months

"Wow amazing result!" I know right? And there's only a 5% chance it's due to statistical error. "That's so impressive! You're so much better than other researchers!" Yeah! 19 other labs tried this experiment and failed — losers!

4

18

454

Grant Slatton

@GrantSlatton

4 months

Being able to apply bulk ad-hoc intelligence to tasks like this makes so many things feasible that weren't before. Doing things like academic research where you need to crawl through huge tomes is going to get so fun and efficient.

3

5

440

Grant Slatton

@GrantSlatton

11 months

Voice commanded essay copilot I always wanted the ability to lean back in my chair and talk an essay into existence, rambling as needed, letting the AI organize my thoughts. Transcription: @ggerganov 's whisper.cpp App: @TauriApps Backend: GPT 3.5 with new functions API

15

68

437

Grant Slatton

@GrantSlatton

1 year

GPT can execute fairly complicated programs as long as you make it print out all state updates. Here is a linear feedback shift register (i.e. pseudorandom number generator). Real Python REPL for reference.

11

44

435

Grant Slatton

@GrantSlatton

1 month

@powerbottomdad1 get me an IV drip

1

392

Grant Slatton

@GrantSlatton

2 months

I'm gonna be so disappointed if humanity doesn't discover any better ML techniques and AGI winds up just being GPT-19 with 100T parameters and 10 billion token context window or something dumb like that It would probably work, but would just be such a let-down

60

11

370

Grant Slatton

@GrantSlatton

1 year

@goodside @ESYudkowsky You can have success by prompting it to answer, and then getting it to critique its own answer, too.

10

17

368

Grant Slatton

@GrantSlatton

3 months

The world wasn't created 4000 years ago It was created at midnight on January 1st 1970 This explains the "wtf happened in 1971" graphs -- it wasn't the gold standard, it was the simulation we live in stabilizing. The graphs before 1970 aren't real.

21

23

356

Grant Slatton

@GrantSlatton

1 year

Added a full LLM type system and context-free grammar to Python. Includes all typescript types, regexes, and arbitrary grammars. Makes coding programs with LLM calls woven in super easy. Thanks @ggerganov for llama.cpp and @abetlen for llama-cpp-python that enable this.

8

41

342

Grant Slatton

@GrantSlatton

1 month

Every few weeks I feel this urge to buy some solar panels Not to hook up to the grid or put on my roof or anything — in Seattle all our power is already hydro There is just something intrinsically neat about owning these magic wafers that produce power, I can't explain it

13

3

307

Grant Slatton

@GrantSlatton

11 months

Star Trek technology always seemed ridiculous, but the universal translator suddenly seems plausible: when you encounter an alien ship, just quickly exchange a petabyte of corpus data, train an LLM on the ship supercomputer in a few milliseconds, have your chat

14

22

302

Grant Slatton

@GrantSlatton

4 months

@teortaxesTex I'm a high-trust boy living in a low-trust world

2

10

296

Grant Slatton

@GrantSlatton

4 months

@q_star_shaman Been doing this for 3 years and empirically this doesn't seem to happen The typical user is someone who used their last bag on a walk and their dog decided to go a second time

3

2

291

Grant Slatton

@GrantSlatton

2 months

The craziest thing about watching this portrayal of a struggle session during the Cultural Revolution is that I know people in Seattle who would 1000% love to do this to techbros/landlords/hedge funds/whatever

36

46

287

Grant Slatton

@GrantSlatton

2 months

I don't understand why more >$100MM wealthy people don't commission more books Like you could pay a good indie author a decent salary to write books about whatever you want I have a ton of story ideas but no time to write, I would commission soooooo many books

46

13

290

Grant Slatton

@GrantSlatton

2 years

@typewriteralley I am down here now dragging around a giant magnet. Also found some on the low bridge bike path.

18

20

279

Grant Slatton

@GrantSlatton

1 month

Most large software orgs are probably leaving millions of $$ of developer productivity on the table by not hiring 1 guy whose sole responsibility is making the test suite run faster Nobody gets promoted for this task, so nobody does it — should just make it its own role

20

14

280

Grant Slatton

@GrantSlatton

8 months

First time seeing ChatGPT give me 2 possible responses in this style (I did not press the "regenerate response" button). When did this functionality get added? I assume it detected I had corrected it multiple times in a row to trigger this mode. Good way to gather RL data.

22

26

269

Grant Slatton

@GrantSlatton

1 month

@knowclarified I think raw reaction time is probably lower level That is, for an IQ task, you probably want "speed to put the task into a useful mental framework that you can then use to solve the problem" And raw processing speed is a subcomponent of that

11

1

275

Grant Slatton

@GrantSlatton

2 months

@levelsio @Uber You'll want to set your payment method to cash anyway because a lot of Uber drivers there don't have their app configured to accept card at all (because they want to avoid paying taxes)

13

0

266

Grant Slatton

@GrantSlatton

3 months

You really want your high-agency, talented people near the front lines Somewhat related, but the more I think about it, the more I think @sebasbensu basically nailed it in this post

Sebastian Bensusan

@sebasbensu

8 months

3

11

143

3

1

255

Grant Slatton

@GrantSlatton

24 days

@RepeticioMucho Medical professionals, doctors nurses physical therapists etc

1

0

257

Grant Slatton

@GrantSlatton

4 months

I wish we lived in a high-trust society At a ramen shop in Japan a few years ago, rainstorm starts. Old lady owner won't let us leave without giving us an umbrella. Language barrier, but the vibe was "just bring it back tomorrow" Can you imagine trusting strangers like that?

29

8

242

Grant Slatton

@GrantSlatton

1 month

Solved by getting the LLM to simulate the execution of a program that carefully prints out every state mutation and logic operator Mapping onto A,B,C,D made it work better due to tokenization (OP said this was fine) Claude beats GPT for this one

Taelin

@VictorTaelin

1 month

Mandatory clarifications and thoughts: 1. This isn't a tokenizer issue. If you use 1 token per symbol, GPT-4 / Opus / etc. will still fail. Byte-based GPTs fail at this task too. Stop blaming the tokenizer for everything. 2. This tweet is meant to be an answer to the following…

45

50

888

13

14

246

Grant Slatton

@GrantSlatton

23 days

Let’s gooooooo

Nat Friedman

@natfriedman

23 days

@sincethestudy Grant inbound. Make it happen!

28

22

727

2

5

222

Grant Slatton

@GrantSlatton

4 months

I don't really trust anyone who thinks they can solve metabolism with any one simple trick

20

14

213

Grant Slatton

@GrantSlatton

1 month

A lot of the appeal of programming is that the computer is always right There is nobody to blame for problems except yourself All issues are skill issues — that clarity is nice

14

19

215

Grant Slatton

@GrantSlatton

10 months

Big news hidden in the OpenAI GPT4 public availability announcement: a gpt-3.5-turbo-instruct model! Been wanting this for a long time. gpt-3.5-turbo is chat-tuned which makes it much harder to use than davinci for tasks that are better structured as completions.

3

19

187

Grant Slatton

@GrantSlatton

2 months

Wanted to update my pfp with my short haircut, but not change the general layout because people recognize you by the thumbnail Seemed like a perfect application of AI image editing I tried 5 different popular apps and none came close to @dingboard_ at ease of use or outcome

9

3

186

Grant Slatton

@GrantSlatton

10 months

Talked to a neuroscience researcher friend who leads a lab here in Seattle. I knew his team had been using ChatGPT a lot since it was released, but was interesting to catch up now that it's been a few months. Some notes below about use outside of tech for those curious.

2

24

183

Grant Slatton

@GrantSlatton

2 months

Ok so the whole "captchas are getting harder" thing is kind of funny now, but really what does the internet do in 6-12 months when all captchas are truly solved Is everyone gonna have to have some proof-of-human private key? Iris scan? ??? what are we gonna do? seems looming

38

7

180

Grant Slatton

@GrantSlatton

5 months

@eriktorenberg @realGeorgeHotz has been making an incredible demo of hiring at @__tinygrad__ by simply posting open-to-the-public, paid bounty tasks and hiring from the pool of successful individuals What could this model look like for education? Or post-education, or whatever we call it.

9

15

171

Grant Slatton

@GrantSlatton

1 year

Has anyone slapped monte-carlo tree search on top of an LLM yet, with each token selection representing a branch? Use logprobs as the initial node bias and train a discriminator to score the leaf nodes?

20

8

161

Grant Slatton

@GrantSlatton

2 months

Excited to share what I've been working on at @GetRowZero for the last 2 years We've created the world's fastest spreadsheet engine, about 100-1000x faster than Excel or Google Sheets All using your familiar Excel skills! Try it at rowzero[dot]io

Row Zero

@GetRowZero

2 months

We've created the fastest spreadsheet!

2

7

48

18

17

159

Grant Slatton

@GrantSlatton

2 months

It will never stop being funny to me that my 35 year old piece of shit Japanese mini truck is better than modern trucks in every way that matters - 6.5ft bed - Sides fold down for flatbed - Easy to maneuver on a jobsite - Trivial to maintain/repair - Better fuel economy

16

2

156

Grant Slatton

@GrantSlatton

5 months

I'm not in the habit of actively wishing for AI to take anyone's jobs... but in the case of the 50% who might've killed my wife... ¯\_(ツ)_/¯

3

154

Grant Slatton

@GrantSlatton

1 month

The Seattle Fire Department is the #1 opposition to adding any traffic calming in the city The number of people who die in car crashes versus fires differs by 100x, so in the grand scheme of things, the fire department is actually net killing people

Devon ☀️

@devonzuegel

1 month

Most people don't realize how much fire departments drive the quality of our street design

5

6

124

5

12

153

Grant Slatton

@GrantSlatton

4 months

Cities should deputize neighborhood locals to do stuff like fill potholes You know how many retired grandpas would love to be the pothole king of their neighborhood? You don't even need to pay these guys, just supply the materials & offer training Cheaper & faster

16

2

153

Grant Slatton

@GrantSlatton

4 months

It was a good lesson though — in life you’ll encounter people who want to create organizations/legibility so that they can be on the top of that hierarchy

3

5

148

Grant Slatton

@GrantSlatton

10 months

The benefit of plain N^2 transformers is you correlate *all* the tokens, and won't tend to miss much. Abandoning N^2 means making heuristic choices about which tokens to correlate. Figuring out a good heuristic is a million (billion?) dollar question.

AK

@_akhaliq

10 months

LongNet: Scaling Transformers to 1,000,000,000 Tokens paper page: Scaling sequence length has become a critical demand in the era of large language models. However, existing methods struggle with either computational complexity or model expressivity,…

18

161

706

5

17

150

Grant Slatton

@GrantSlatton

2 months

I'm surprised some pro-natalism billionaire hasn't funded the creation of an actually good and healthy dating app designed to actually get people into committed relationships and off the hedonic treadmill

EigenGender

@EigenGender

2 months

Probably dating apps just need to be operated as a public service. Absolutely massive amounts of consumer surplus and any attempt to capture nontrivial amounts of that surplus is insanely destructive

24

25

621

22

10

149

Grant Slatton

@GrantSlatton

4 months

@ByrneHobart The cosine similarity of those two tokens in the latent space is pretty small, easy mistake for a neural network to make early in the training run

2

3

145

Grant Slatton

@GrantSlatton

8 months

GPT4 cannot play chess. Expected to get a bot up to ~1000 Elo and totally failed -- but negative results are still interesting! Even given verbose prompting, board state descriptions, CoT, etc, it loses badly to depth=1 engine. Code & notes below.

26

15

144

Grant Slatton

@GrantSlatton

8 months

Altman always says "we were surprised nobody built ChatGPT first". Folks made chatbots with GPT3, they just cost a fortune to run, of course nobody released a free website. Pictured: my friend trying to jailbreak my Twilio SMS GPT3 bot over a year ago

Aidan McLau

@aidan_mclau

8 months

For months I’ve loudly asked for a great conversational assistant. OpenAI finally shipped it. And, just like ChatGPT, the developer community dropped the ball. There is no secret-sauce here. It’s just Whisper -> GPT -> TTS. Devs had these tools since March

95

17

404

6

3

142

Grant Slatton

@GrantSlatton

8 months

The new model readily beats Stockfish Level 4 (1700) and still loses respectably to Level 5 (2000). Never attempted illegal moves. Used clever opening sacrifice, and incredibly cheeky pawn & king checkmate, allowing the opponent to uselessly promote.

3

4

135

Grant Slatton

@GrantSlatton

4 months

I'm pretty sure the top 25% or so of public school kids would be better off if you just left them alone to read the textbooks and help each other as needed It turns out textbooks are written by smart people and tend to be much better than the median teacher for certain students

9

5

132

Grant Slatton

@GrantSlatton

8 months

@BorisMPower Interestingly, in the games it lost again higher rated Stockfish bots, even after GPT made a bad move, it was still able to *predict* Stockfish's move that takes advantage of GPT's blunder. So you could probably get a >2000 Elo GPT by strapping on a tiny bit of search.

9

4

131

Grant Slatton

@GrantSlatton

3 months

@charlieboardman One of the best business books I have ever read, absolutely packed full of great business/marketing/management lessons, and fascinating history/stories

3

126

Grant Slatton

@GrantSlatton

5 months

Since this experience, whenever I make friends with a new doctor, I quiz them to see if they would have correctly diagnosed the issue Around 50% get it right, and to the ones who get it right, it's obvious and they're astounded anyone with a medical license could get it wrong

1

0

125

Grant Slatton

@GrantSlatton

3 months

Sam Altman could do the funniest thing ever by releasing GPT5 fifteen minutes before Superbowl kickoff

3

2

126

Grant Slatton

@GrantSlatton

1 year

The impact AI will have on the field of history is underrated. AI will read every cuneiform tablet, monastic scroll, 17th century diary, understand every ancient language natively, and be able to synthesize a coherent view of history from every point of view.

7

13

125

Grant Slatton

@GrantSlatton

2 months

@levelsio @fede_intern @Uber Yes all these people are talking about the case where you would have brought USD cash in to exchange for the gray market rate (which is what all locals do) The ATM rate is about 15% worse than the gray market rate (it used to be like 3x worse a few months ago, but Milei fixed)

4

1

119

Grant Slatton

@GrantSlatton

4 months

@nabeelqu He had that dawg in him But really you see this with a lot of the FIRE guys -- many people who have the dedication to build a business and amass enough wealth to retire by mid-30s are also the kind of guy who can't sit still and needs to build

2

0

118

Grant Slatton

@GrantSlatton

4 months

Junior engineers who just learned about microservices doing system design

8

7

115

Grant Slatton

@GrantSlatton

4 months

Riffing on this idea a bit, I think you'll see a resurgence of languages more akin to prolog where you codify the properties you want some code to have, and the runtime uses intelligence to figure out the optimal implementation

will depue

@willdepue

4 months

I have a long-standing prediction that software will be written in increasingly low level languages due to the cost of development and maintenance drops with AI. high level prompts, low level code, best possible performance and customizability.

32

17

391

11

7

113

Grant Slatton

@GrantSlatton

8 months

@gigafestyu According to lichess by move 6 there is no recorded game that matches this one.

2

1

112

Grant Slatton

@GrantSlatton

4 months

Every codebase tends to be extended to the point of incomprehensibility If people can comprehend it, they will extend it, and will keep doing so until it's not comprehensible -- in the long run, all codebases become incomprehensible Peter Principle but for code

13

6

111

Grant Slatton

@GrantSlatton

3 months

Carpenters if they were like junior software developers: “I went to add a shelf but found the house is framed with pine instead of cedar, so anyway I tore down the house and am rebuilding it”

8

5

110

Grant Slatton

@GrantSlatton

4 months

@rshakoor12 Many such cases

0

110

Grant Slatton

@GrantSlatton

8 months

In conclusion, I now totally believe @BorisMPower 's claim about 1800 Elo for GPT4. I think the RLHF'd chat models do not do this well, but the base/instruct models seem to do much better.

Boris Power

@BorisMPower

9 months

@francoisfleuret I don’t think anything has been published unfortunately. ELO is around 1800

4

0

23

4

1

109

Grant Slatton

@GrantSlatton

1 month

It's a shame there isn't more research put into non-lethal guns Fundamentally I think people have the right to defend themselves from assault But I wish there were more options that were just as effective as a gun but less lethal Why no full-auto self-targeting tasers??

42

4

111

Grant Slatton

@GrantSlatton

4 months

@sgondala2 @AskMarvinAI is a very useful little library for quick scripts like this

3

109

Grant Slatton

@GrantSlatton

5 months

Was a TA for algorithms class. Made an automated grader: student uploads program, run 100 test cases, score is % correct Once a student got 99%, missed a small edge case I'd email students to offer hints. He responds "99% is fine, thanks though" Broke my perfectionist brain

4

3

107

Grant Slatton

@GrantSlatton

3 months

I loved this bit about Internet Writing as a discipline in the recent @dwarkesh_sp podcast with @tylercowen

4

11

106

Grant Slatton

@GrantSlatton

5 months

@alexgraveley It's funny how people have their own "this one thing will teach you everything you need to know" (and I totally believe all of them) For me, it's "write a disk-backed, log-structured merge tree KV store with REST API" -- this one project will teach you literally everything

6

2

103