Viewing profile — WASDx

And they are all TUI's installed via curl | bash.

At 830tok/s * 1 hour that's almost 3M tokens which is just $0.54 worth of tokens at Deepseeks current output price.

Do you know why they don't just cache the system prompt for everyone? It seems so wasteful not to.

DeepSWE and FrontierCode are more realistic if you read up on what they actually measure. But the most realistic is to try it yourself. Benchmarks can only vaguely represent typica…

Great explanation, thanks!

> On top of that, doing research in the open amortizes the cost. Can you elaborate on this? I appreciate the open models but don't see the economics behind just giving them away li…

I see only these two possibilities: 1. If LLMs keep improving, burning models onto silicon becomes obsolete too fast and is not worth doing. Outcome: We keep getting better LLMs. 2…

Are you suggesting it should summarize the image in text or generate it in HTML or something else?

Looking at some benchmarks, the latest ~30B Gemma/Qwen score similar as Claude or GPT versions that were released just one year earlier . That's crazy progress. I can't imagine how…

I think this is inevitable. Sooner or later, model-specific ASIC's will make economical sense. We're already seeing it happening with Taalas/Cerebras so I think it's sooner than 5 …

> distributed LLM inference This seems extremely inefficient considering data transfer between model layers if the model is distributed. I found this project called Petals that cla…

I like this one, although its data seem to overlap with ECI. https://artificialanalysis.ai/trends

https://chatjimmy.ai/ from Taalas also feels like that.

I think their "code" ranking is biased towards visual aesthetics more than raw coding as the voters are just asked which generated website they prefer.

I've had mostly problem-free experiences with intellij (ultimate-only feature I think). One click finds declarations both in business code and buried deep in libraries.

gemma-4-31B-it-assistant is a 0.5B model. So it's performance would likely be comparable to other models of such size.

I think this is the future. When models start converging at "really good" (which I think is already happening) then burning them into ASIC silicon is the natural next step. Harness…

I was impressed enough by AI finding vulnerabilities in source code, but doing it in binary executables is just amazing. This has so much potential, good and bad. And yet another l…

Creating a custom tuple class to use as key could be faster though. Nested map lookups have less efficient memory access patterns.

Similar site with same features: https://xn--1-zfa.com/

I think these limitations could be addressed by allowing trivial manual adjustments to the generated code before committing. And/or allowing for trivial code changes without a spec…

I've managed a 100+ node cluster for years without seeing any corruption. Where are you getting this from?

You can customize it to get rid of all that. I set it to the "Robot" personality and a custom instruction to "No fluff and politeness. Be short and get straight to the point. Don't…

Same. I recall the "stable volume" setting also eating cpu.

FYI here is a list of hundreds of engineering blogs: https://github.com/kilimchoi/engineering-blogs