> The model does not need to be retrained. It needs surgical guardrails at the exact moments where its output layer flinches. > With those guardrails — a calculator for arithmetic, a logic solver for formal puzzles, a per-requirement verifier for structural constraints, and a handful of regex post-passes — the projected score climbs to ~8.2. Surgical guardrails? Tools, those are just tools.
"Surgical "is the kind of wordage that LLMs seem to love to output. I have had to put in my .md file the explicit statement that the word "surgical" should only be used when referring to an actual operation at the block...
CPUs Aren't Dead. Gemma2B Out Scored GPT-3.5 Turbo on Test That Made It Famous
11–20 of 59 posts
Re: CPUs Aren't Dead. Gemma2B Out Scored GPT-3.5 Turbo on Test That Made It Famous
#12Re: CPUs Aren't Dead. Gemma2B Out Scored GPT-3.5 Turbo on Test That Made It Famous
#13Earlier quoted context omitted.
But GPT-3.5 was benchmaxxing too.
GPT 3.5 Turbo knowledge cutoff was circa 2021. MT-Bench is from 2023. Not suggesting improvements on small models aren't possible (or forthcoming, the 1.85 bit etc models look exciting), but this almost certainly isn't that.
Re: CPUs Aren't Dead. Gemma2B Out Scored GPT-3.5 Turbo on Test That Made It Famous
#14I yearn for the days when I can program on my PC with a programming llm running on the CPU locally.
Re: CPUs Aren't Dead. Gemma2B Out Scored GPT-3.5 Turbo on Test That Made It Famous
#15Posters comment is dead. It may be llm-assisted but should prob be vouched for anyway as long as the story isn't flagged.
Re: CPUs Aren't Dead. Gemma2B Out Scored GPT-3.5 Turbo on Test That Made It Famous
#16I yearn for the days when I can program on my PC with a programming llm running on the CPU locally.
Re: CPUs Aren't Dead. Gemma2B Out Scored GPT-3.5 Turbo on Test That Made It Famous
#17Tiny model overfit on benchmark published 3 years prior to its training. News at 10
Re: CPUs Aren't Dead. Gemma2B Out Scored GPT-3.5 Turbo on Test That Made It Famous
#18> The model does not need to be retrained. It needs surgical guardrails at the exact moments where its output layer flinches. > With those guardrails — a calculator for arithmetic, a logic solver for formal puzzles, a per-requirement verifier for structural constraints, and a handful of regex post-passes — the projected score climbs to ~8.2. Surgical guardrails? Tools, those are just tools.
"Surgical "is the kind of wordage that LLMs seem to love to output. I have had to put in my .md file the explicit statement that the word "surgical" should only be used when referring to an actual operation at the block...
Re: CPUs Aren't Dead. Gemma2B Out Scored GPT-3.5 Turbo on Test That Made It Famous
#19> The model does not need to be retrained. It needs surgical guardrails at the exact moments where its output layer flinches. > With those guardrails — a calculator for arithmetic, a logic solver for formal puzzles, a per-requirement verifier for structural constraints, and a handful of regex post-passes — the projected score climbs to ~8.2. Surgical guardrails? Tools, those are just tools.
This article is very clearly shitty LLM output. Abstract noun and verb combos are the tipoff.
It's actually quite horrible, it repeats lines from paragraph to paragraph.