Path: csiph.com!eternal-september.org!feeder3.eternal-september.org!news.iecc.com!.POSTED.news.iecc.com!nerds-end From: antispam@fricas.org Newsgroups: comp.compilers Subject: Re: AI for optimization? Date: Sun, 25 May 2025 22:11:24 -0000 Organization: Compilers Central Sender: johnl%iecc.com Approved: comp.compilers@iecc.com Message-ID: <25-05-020@comp.compilers> References: <25-05-016@comp.compilers> <25-05-018@comp.compilers> MIME-Version: 1.0 Content-Type: text/plain; charset="UTF-8" Injection-Info: gal.iecc.com; posting-host="news.iecc.com:2001:470:1f07:1126:0:676f:7373:6970"; logging-data="62811"; mail-complaints-to="abuse@iecc.com" Keywords: optimize, comment Posted-Date: 25 May 2025 18:28:56 EDT X-submission-address: compilers@iecc.com X-moderator-address: compilers-request@iecc.com X-FAQ-and-archives: http://compilers.iecc.com Xref: csiph.com comp.compilers:3663 arnold@freefriends.org wrote: > In article <25-05-016@comp.compilers>, > wrote: >>I am just surprised that I read and hear so much about work based on LLMs, which >>seems to be a dubious technology for doing things where correctness is >>important. What am I missing? > > The fact that AI is "hot" right now? "Sexy"? "Good for getting > startup capital"? Who cares about correctness? > > Pardon my cynicism. I samewhat different spirit: LLM folks have a lot of money for research. They try to apply LLMs to various things, it does not matter if those trials make senss or not. In the process they improve their machinery and may get some possible applications. Concerning correctness, one possible variation is to treat LLMs as heuristic search, which may find some gems but also may produce garbage. For me it would be natural to combine that with more reliable technology. Possible combionations: - optimization hints for classic compilers (in some cases that may involve inventing more precise types), if hints are wrong optimization would not fire or would not lead to improvement in runtime. - LLM produced proofs. Compiler would check the proofs and reject wrong ones. Of course we will see companies applying LLMs techniques with little checks, but this is due to how companies works, if not LLMs than something else would be abused. -- Waldek Hebisch [See the two papers I recently sent out, which use LLMs to do C to Rust conversion but have feedback to say whether the conversion was correct. -John]