Trying to recall... # 27B GGUF # Benchmark results: # - TG speed: ~5 tok/s (vs baseline ~4.5 tok/s, +10% improvement) # - PP speed: ~60 tok/s (stable across context sizes) # - With parallel=4: total throughput ~28 tok/s…
Very cool. Anything publicly available?
Same happened to me. I only had to ask the service where to tap exactly.
For me the combination of agentic search and deep wiki creation for legacy code bases is a killer app/game changer. Not for the surviving authors of the legacy code bases.
Whay about of the tons of caches that just pile up until you notice that you must delete them manually?
I also have an M1 Max 64GB: Qwen 3.6 benefits from MTP (after rounds of parameter optimization). MLX was unstable (haven't tried it recently), faster at TG but slower at PP, so inconclusive.
https://github.com/microsoft/skills/tree/main/.github/plugin... is similar, works for Claude Code, too. I ported it to Pi: https://pi.dev/packages/@amb007/deep-wiki?name=deep-wiki Elsewhere, I added deep-wiki:lookup…
Essentials of Programming Languages 1st ed. is special
About deployment to cloud: https://news.ycombinator.com/item?id=38988238
https://icfp24.sigplan.org/home/minikanren-2024#event-overvi... is related. There has been work on turning slow bidirectional code into faster functional code (in 2023, reachable from this url).
Something like (in software, trying to understand) a spaghetti monolith?
Code rusts via the loss of information about it (memory, documentation...). If it cannot be maintained, it is a zombie.
OK, I realized it was about something else. I don't follow Uncle Bob, and was referring to some people justifying "unclean"/incorrect shortcuts to gain performance.
Nicely put. I also spent decades in the SW industry, tried about a dozen things, but chose to stay out of management. For me, business and engineering are two completely different areas, often conflicting, and my…
Wrong. Performance and correctness/cleanness go together. Perhaps you have never tried generating correct code that is ways faster than what you can write by hand.
https://www.cs.tufts.edu/~nr/cs257/archive/norman-ramsey/mat... by the current Microsoft CTO
https://www.mg.edu.rs/en#gsc.tab=0
Plain entropy. I use an extension for killing duplicate tabs, helps a lot.
I would appreciate if someone wrote here their opinion on Matriarch [1], an application of category theory to biology/physics via software. [1] https://web.mit.edu/matriarch/
You can handle any language with a read-time parser, then work with ASTs, pretty-print the result in another language. In between, it's just Lisp.
You can wrap a code generator by a macro.
https://en.wikipedia.org/wiki/K%C3%BCstendorf
No, rather in the category of endocrine functors.
https://en.uncyclopedia.co/wiki/Philip_Glass
Math must be understood, cannot be learned just by heart, unlike most other facts.
Trying to recall... # 27B GGUF # Benchmark results: # - TG speed: ~5 tok/s (vs baseline ~4.5 tok/s, +10% improvement) # - PP speed: ~60 tok/s (stable across context sizes) # - With parallel=4: total throughput ~28 tok/s…
Very cool. Anything publicly available?
Same happened to me. I only had to ask the service where to tap exactly.
For me the combination of agentic search and deep wiki creation for legacy code bases is a killer app/game changer. Not for the surviving authors of the legacy code bases.
Whay about of the tons of caches that just pile up until you notice that you must delete them manually?
I also have an M1 Max 64GB: Qwen 3.6 benefits from MTP (after rounds of parameter optimization). MLX was unstable (haven't tried it recently), faster at TG but slower at PP, so inconclusive.
https://github.com/microsoft/skills/tree/main/.github/plugin... is similar, works for Claude Code, too. I ported it to Pi: https://pi.dev/packages/@amb007/deep-wiki?name=deep-wiki Elsewhere, I added deep-wiki:lookup…
Essentials of Programming Languages 1st ed. is special
About deployment to cloud: https://news.ycombinator.com/item?id=38988238
https://icfp24.sigplan.org/home/minikanren-2024#event-overvi... is related. There has been work on turning slow bidirectional code into faster functional code (in 2023, reachable from this url).
Something like (in software, trying to understand) a spaghetti monolith?
Code rusts via the loss of information about it (memory, documentation...). If it cannot be maintained, it is a zombie.
OK, I realized it was about something else. I don't follow Uncle Bob, and was referring to some people justifying "unclean"/incorrect shortcuts to gain performance.
Nicely put. I also spent decades in the SW industry, tried about a dozen things, but chose to stay out of management. For me, business and engineering are two completely different areas, often conflicting, and my…
Wrong. Performance and correctness/cleanness go together. Perhaps you have never tried generating correct code that is ways faster than what you can write by hand.
https://www.cs.tufts.edu/~nr/cs257/archive/norman-ramsey/mat... by the current Microsoft CTO
https://www.mg.edu.rs/en#gsc.tab=0
Plain entropy. I use an extension for killing duplicate tabs, helps a lot.
I would appreciate if someone wrote here their opinion on Matriarch [1], an application of category theory to biology/physics via software. [1] https://web.mit.edu/matriarch/
You can handle any language with a read-time parser, then work with ASTs, pretty-print the result in another language. In between, it's just Lisp.
You can wrap a code generator by a macro.
https://en.wikipedia.org/wiki/K%C3%BCstendorf
No, rather in the category of endocrine functors.
https://en.uncyclopedia.co/wiki/Philip_Glass
Math must be understood, cannot be learned just by heart, unlike most other facts.