From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mx.treblig.org (mx.treblig.org [46.235.229.95]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 31C8F36165F; Mon, 9 Mar 2026 18:53:52 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=46.235.229.95 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1773082435; cv=none; b=HQ2hNMHzFLS587V+cunAt2XHooQbeBgY0JP9IOJhJk+Bu9XI+QW2rBa71TD0m1I2OzSWXZA8MCcSMi6FgSlyRRHOkX4ZCnvKKO2tq4khYNKgHZHrQYVBljP52+MfxfRGvxgt30HXrJWTOjOLS0BCIL+pFkqms60Ol5BsdguW00Q= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1773082435; c=relaxed/simple; bh=K5iBIIK5ObkFxFQE4+AEduOJB6sfGk2EHjZ7be1uuDk=; h=Date:From:To:Cc:Subject:Message-ID:References:MIME-Version: Content-Type:Content-Disposition:In-Reply-To; b=iok2CTEoe6rtWqH83A8Vbad0ZM/HVTlTbVOr9NZtHCKBCeeNqkZpUzk/Je+0P1FcIx2HD3LlDLsUmZxPxODpGXh4NKj2LFkocEQNfUZkn5d6Ik5VMUamEL2wIh9ZAKu7yAdl7ojU0LCy8mCelGYGfHwQCV5Jtqwx2JHSOeFNIZg= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=treblig.org; spf=pass smtp.mailfrom=treblig.org; dkim=pass (2048-bit key) header.d=treblig.org header.i=@treblig.org header.b=Dz7fagG7; arc=none smtp.client-ip=46.235.229.95 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=treblig.org Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=treblig.org Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=treblig.org header.i=@treblig.org header.b="Dz7fagG7" DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=treblig.org ; s=bytemarkmx; h=Content-Type:MIME-Version:Message-ID:Subject:From:Date:From :Subject; bh=GKJwQu5tU7RD/ETEBVJidUUwN+tE/o+2GDFUBN+p62Y=; b=Dz7fagG7ah+JFR8T OwTLRNTqRAh/M0fwqC4el0I+hbd/MnVwTwzL1aVwyVbuK9RE6Ogw6XWJxXMAqD6cN4awgGFuUXdBB 84a33Zvk7kJ7lIMkGIWwvnqLdNY5c5D1D6E7WqWMj04Edl32PmTQgkRpefcyL6Yk20V1Z1KsWzYj4 4dWU11yrZMkOlOq/ZN6aSiTxM1VbMTra2t5CFxToMnd2bDAJ/X/1135YaMxr1BRQ1MUHAXPz0ID4M 2vDLmBziAZnI+c6i5nxUaQwwlMB1se7TBPj2lyNVqv5uBge2LW9TLmoXOZK+xyuW9UX0aSDjWVUVj ZFvjggVR+r2NcbCSXg==; Received: from dg by mx.treblig.org with local (Exim 4.98.2) (envelope-from ) id 1vzfUj-00000008Jg4-1uml; Mon, 09 Mar 2026 18:38:21 +0000 Date: Mon, 9 Mar 2026 18:38:21 +0000 From: "Dr. David Alan Gilbert" To: Steven Rostedt Cc: James Bottomley , "H. Peter Anvin" , Jonathan Corbet , Christian Brauner , tech-board-discuss@lists.linux.dev, linux-kernel@vger.kernel.org, ksummit-discuss@lists.linuxfoundation.org, christianvanbrauner@gmail.com Subject: Re: LLM based rewrites Message-ID: References: <20260307-clean-room-6118793eb175@brauner> <20260309095705.7a6b6177@gandalf.local.home> <20260309121629.21cabc25@gandalf.local.home> <871phtvu7r.fsf@trenco.lwn.net> <04B897EF-DEEC-42D0-8E00-888CEEA5318E@zytor.com> <1caf74551e06ef43e4cc6829c961c1de2bbf8758.camel@HansenPartnership.com> <20260309143406.3d45e36e@gandalf.local.home> Precedence: bulk X-Mailing-List: tech-board-discuss@lists.linux.dev List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Disposition: inline In-Reply-To: <20260309143406.3d45e36e@gandalf.local.home> X-Chocolate: 70 percent or better cocoa solids preferably X-Operating-System: Linux/6.12.48+deb13-amd64 (x86_64) X-Uptime: 18:35:33 up 133 days, 18:11, 2 users, load average: 0.10, 0.03, 0.01 User-Agent: Mutt/2.2.13 (2024-03-09) * Steven Rostedt (rostedt@goodmis.org) wrote: > On Mon, 09 Mar 2026 11:19:42 -0700 > James Bottomley wrote: > > > I don't think LLMs will be able to come up with the necessary proof of > > separation without essentially recreating the clean room process, which > > grows cost prohibitive as the complexity of the work increases. > > I con see one AI bot reading the original code, and then making the prompts > to pass to a second AI bot to produce the code. That's what Chardet did: https://github.com/chardet/chardet/issues/327#issuecomment-4005195078 however, there's a fun question of whether the second AI had already seen the code; a lot of LLMs seem to have been trained on a lot of open source code already. Dave > -- Steve > -- -----Open up your eyes, open up your mind, open up your code ------- / Dr. David Alan Gilbert | Running GNU/Linux | Happy \ \ dave @ treblig.org | | In Hex / \ _________________________|_____ http://www.treblig.org |_______/