Kipping pull-ups, who does them and can explain the benefits over regular ones to me? Never even bothered to do them, sure, volume is higher but for me it’s like doing push-ups without straightening your arms, just bad form.

Easing back into Yoga again, a week of restorative practice, sitting and programming all day takes its toll, more than I expected, hamstrings are the first that criminally shorten, followed by knee problems.

Always a gamble with the top gaming cards, last years it was crypto mining, now it is the US ban of AI chips to China like the H100, A100, H800, A800, and L40S, therefore the RTX 4090 series cards get salvaged and repurposed for model training in smaller data centers.
Market price in China is $400-900 higher, so scalpers make a killing with those cards.

As the codex based github copilot shows its age, I am in search of a better LLM for Python code completion.
The benchmark that measures the performance is called HumanEval.
Found this interesting site which a chart on Code Generation on HumanEval.
Together with some open source models and xAIs new Grok-1, this is the top 20:

1.) Language Agent Tree Search (GPT-4) 94.4%
2.) Reflexion (GPT-4) 91.0%
3.) Language Agent Tree Search (GPT-3.5) 86.9%
4.) OctoPack (GPT-4) 86.6%
5.) ANPL (GPT-4) 86.6%
6.) Parsel (GPT-4 + CodeT) 85.1
7.) MetaGPT (GPT-4) 81.7%
8.) ANPL (GPT-3.5) 76.2%
9) Phind-CodeLlama-34B-v2 73.8%
10.) WizardCoder-Python-34B-v2 73.2%
11.) Claude 2 70%
12.) Phind-CodeLlama-34B-Python-v1 69.5%
13.) GPT-4 67%
14.) CODE-T (code-davinci-002) 65.8%
15.) CODE-T-Iter (code-davinci-002) 65.2%
16.) Grok-1 63.2%
17.) Unnatural Code Llama 62.2%
18.) PanGu-Coder2 15B 61.64%
19.) WizardCoder 15B 57.3%
20.) Code Llama - Python 53.7%
.
.
.
36.) Codex-12B/copilot 28.81%

I tried WizardCoder-Python-34B-v2 already via llama-cpp-python server in visual studio code, but it is not that fast for me as cuda support is still in early development. Some other alternatives I can test are vllm, flexflow, LocalAI, FastChat and OpenLLM.

So the best options for me are:

1.) OpenAI API (GPT-4)
2.) OpenAI API (GPT-3)
3.) Self hosted 6bit or 8bit quantized Phind-CodeLlama-34B-v2


https://paperswithcode.com/sota/code-generation-on-humaneval

I learned a few programming languages in my life, starting from BASIC, Turbo Pascal, C++, shell script, perl, php, javascript, python, some I even forgot, like assembler, microprocessor programming or lisp as part of AutoCAD in school. I'm sure there were more I forgot.