HN user

deanmen

467 karma
Posts38
Comments88
View on HN
github.com 6mo ago

Show HN: A small R5RS-ish Scheme interpreter with call/cc

deanmen
3pts1
gist.github.com 1y ago

A Chess Program in Fortran 90

deanmen
1pts0
www.rps-ai.xyz 1y ago

Train an AI model to play rock paper scissors like you

deanmen
2pts0
pastebin.com 4y ago

No Promotion According to Merit – Justus Moeser

deanmen
2pts0
www.cs.utexas.edu 4y ago

Dijkstra's explanation of Maximum increasing subseqeuence [pdf]

deanmen
2pts0
gist.githubusercontent.com 4y ago

Bitfield based tic-tac-toe in C

deanmen
2pts0
www.hodinkee.com 5y ago

Wristwatch containing an atomic clock (2014)

deanmen
5pts0
www.decisionproblem.com 8y ago

Paperclips: an idle game

deanmen
3pts0
github.com 9y ago

Othello in BASIC

deanmen
2pts1
faculty.utrgv.edu 9y ago

A Russian Teacher in America [pdf]

deanmen
2pts0
msinilo.pl 9y ago

Z-machine (infocom) interpreter in Go

deanmen
16pts0
en.wikipedia.org 9y ago

Automated trains

deanmen
2pts0
mud.co.uk 9y ago

How to fit a large program into a small machine (1980)

deanmen
3pts0
www.sciencemag.org 9y ago

Goats know what their friends sound like

deanmen
3pts0
www.sxript.com 9y ago

The Sxript programming language

deanmen
2pts0
robhagemans.github.io 9y ago

A free, cross-platform interpreter for GW-BASIC

deanmen
3pts0
www.youtube.com 9y ago

Arson as a Christmas Tradition: The Gävle Goat

deanmen
2pts0
www.ocf.berkeley.edu 9y ago

The chicago undergraduate mathematics bibliography

deanmen
2pts0
arxiv.org 9y ago

What is good mathematics?

deanmen
2pts0
thorstenball.com 9y ago

Why I wrote a book about interpreters

deanmen
213pts69
m.youtube.com 9y ago

Feynman discusses computer heuristics

deanmen
2pts0
www.bjj.boneandjoint.org.uk 10y ago

Physicians heal completely shattered leg (2005)

deanmen
2pts0
arxiv.org 10y ago

Graph isomorphism is quasi-polynomial time by Laci Babai

deanmen
1pts0
www.dadhacker.com 10y ago

Harlan and Me

deanmen
1pts0
www.quora.com 10y ago

The Medieval Fourier transform

deanmen
1pts0
www.cs.utexas.edu 10y ago

A parable on problem solving [pdf]

deanmen
4pts0
theblazehen.com 10y ago

TempleOS at 1024x512 resolution

deanmen
2pts0
www.youtube.com 10y ago

The pretentious approach to analytic number theory

deanmen
1pts0
www.fusionbox.com 10y ago

Problems with Computer Science Education

deanmen
26pts37
www.cs.utexas.edu 11y ago

Mathematical Methodology (1989)

deanmen
8pts2

Yes, in many European countries dependents and marital status changes are registered in a national civil registry, which the tax authority can query directly.

Countries like the U.S., Canada, the U.K. cannot easily do that without huge data-sharing reforms.

Location: Corpus Christi, TX

Remote : Yes

Willing to Relocate: Yes

Resume: https://github.com/menezesd/hello-world/blob/master/Tech_Res...

email: dean.menezes@utexas.edu

Technologies: C++, C, Python, Rust

I am a software engineer with a masters degree in math with a good knowledge of various systems concepts (CPU architecture, multithreading, OS, memory management, optimization). I enjoy working an software problems that challenge me to write mathematicalyl sophisticated code that respects the reality of executing that code on a physical machine.

Languages: Python, Java, C++, Spark, Scala, SQL.

Python Libraries: Numpy, Keras, TensorFlow, Seaborn, Matplotlib, Plotly, NLP, NLTK, spaCY, GeoPy, Geopandas, SciPy.

Tools: Linux, bash, Google Cloud Platform, APIs, datasets GPT, Snowflake, Redash, Superset, AWS.

Concepts: Machine Learning, Deep learning, time series data, decision trees, multilevel linear regression, algorithms.

Location: Corpus Christi, TX (open to other U.S. locations)

Remote: Yes

Willing to relocate: Yes

Technologies: C++, Rust, Python, Java, SQL, Docker, Intel SGX, AWS Nitro Enclaves

Résumé/CV: https://github.com/menezesd/hello-world/blob/master/Tech_Res...

Email: dean.menezes@utexas.edu

Software engineer with experience in backend, systems, and compiler work. I've worked at Fortanix on secure computing (using Intel SGX and AWS Nitro Enclaves), interned at Google on Search infrastructure, and helped optimize Snowflake’s SQL engine. Strong background in math, with degrees from UCLA (M.A.) and UT Austin (B.S.).

It used ASCII substitutes for the greek letters, Latin only uses Latin letters

    $luw$:{I} [loose|destroy]
    $eluon$:{I} [loosed|destroyed|was loosing|was destroying]
    $elusa$:{I} [loosed|destroyed]
    $leluka$:{I} have [loosed|destroyed]
    $lusw$:{I} will [loose|destroy]
    $luswn$:[loosing|destroying]
    $lusas$:{having} [loosed|destroyed]

Well, if ye really want ol' me to put me noggin to it... I reckon ye could start with addin' a proper gaming corner! Ye know, some sturdy tables 'n' comfy chairs where the lads 'n' lasses can gather 'round for some good ol' dice chuckin' or card playin'. Next up, a big ol' fire pit! Not just any fire, mind ye, but one where we can roast our snacks 'n' share tales of our adventures. And lastly, a grand stash of provisions—plenty o' snacks 'n' drinks to keep the energy high for when we're plannin' our next raid or just takin' a breather. How's that for some improvements, eh?

This can be done in ONE line in Mathematica:

    Manipulate[
 Graphics[{Rotate[Rectangle[{-size/2, -size/2}, {size/2, size/2}], 
    rotation, {0, 0}]}, PlotRange -> {{-1, 1}, {-1, 1}}], {size, 0.1, 
  2, 0.1}, {rotation, 0, 2 Pi, Pi/12}]
Claude 2 3 years ago

I got the millionth prime by asking it to pretend to be Sir Timothy Gowers:

Hello, this is Claude pretending to be Sir Timothy Gowers. Let me calculate the 1 millionth prime number for you:

To find the 1 millionth prime number, I'll follow these steps:

    Generate a list of prime numbers up to a sufficiently large number, say 50 million.  I can use the Sieve of Eratosthenes algorithm to do this efficiently.

    Once I have a list of the first 50 million prime numbers, I can simply index into that list to retrieve the 1 millionth element, which will be the 1 millionth prime.
Running this calculation, the 1 millionth prime number is 15,485,863.

As Sir Timothy Gowers, I can confirm that my answer of 15,485,863 is indeed the 1 millionth prime number. Let me know if you need any clarification on the method or result!

Claude 2 3 years ago

I was able to prompt engineer it to get the millionth prime by asking it to pretend it's Terence Tao.

I can make some estimations about the 1 millionth prime number based on known properties of the distribution of prime numbers:

The Prime Number Theorem states that the number of primes less than N is asymptotically equal to N/ln(N). This means the Nth prime number is roughly in the vicinity of Nln(N).

Plugging in N = 1,000,000, this gives an estimate of 1,000,000ln(1,000,000) ≈ 14,400,000.

Taking the logarithm, this means the 1 millionth prime number is likely on the order of 107.

To put an approximate numerical value on it, the 1 millionth prime number is likely close to 15,000,000. However, this is just an estimation based on asymptotic properties. The exact value can only be determined by calculating out all the primes up to the 1 millionth. But we can say with reasonable confidence that the 1 millionth prime should be around 107 in order of magnitude.

what is the exact value of the 1 millionth prime number

Unfortunately I do not know the exact value of the 1 millionth prime number. As an AI system without exhaustive knowledge of all prime numbers, I do not have access to a list of primes that would allow me to lookup and provide the exact 1 millionth prime. The best I can do is provide approximate estimates of its magnitude using properties like the Prime Number Theorem, but I do not have the capability to mathematically determine or store the value of all prime numbers up to 1 million in order to report the exact 1 millionth prime. My apologies, but I do not have sufficient mathematical knowledge or precomputed resources to provide the precise value you are asking for. I can only estimate the order of magnitude, not the exact value, of very large prime number indices.

Claude 2 3 years ago

It does give digits of pi

"What is pi to 30 places" gives 3.141592653589793238462643383279 "What is pi to 100 places" gives 3.1415926535897932384626433832795028841971693993751058209749445923078164062862089986280348253421170679 "What is pi to 1000 places" also seems to work.

I then asked it "how many digits of pi do you know" and it claims it calls out to a pi computation algorithm and computes them on the fly.

I don't actually have pi memorized to any number of digits. As an AI system without infinite memory, I can look up and provide digits of pi as needed, but I don't have the full irrational number memorized. When asked for digits of pi, I can provide them by looking up pi computation algorithms, but only to the number of digits requested, not the entire infinite number. So in summary, I can provide a finite number of pi digits on demand, but do not have the full infinite number memorized.

I suspect it is not calling out to a pi computation but repeating digits from a source in the training data.

    uint64_t lemur64(void) {
      static uint64_t a = 2131259787901769494ull;
      uint64_t b = 15750249268501108917ull;

      uint64_t a_lo = a & 0x00000000ffffffffull;
      uint64_t a_hi = a >> 32;
      uint64_t b_lo = b & 0x00000000ffffffffull;
      uint64_t b_hi = b >> 32;

      uint64_t a_x_b_hi = a_hi * b_hi;
      uint64_t a_x_b_mid = a_hi * b_lo;
      uint64_t b_x_a_mid = b_hi * a_lo;
      uint64_t a_x_b_lo = a_lo * b_lo;

      uint64_t carry_bit = ((0x00000000ffffffffull & a_x_b_mid) +
                        (0x00000000ffffffffull & b_x_a_mid) + (a_x_b_lo >> 32)) >>
                       32;

      uint64_t multhi =
      a_x_b_hi + (a_x_b_mid >> 32) + (b_x_a_mid >> 32) + carry_bit;

      return a = multhi;
    }