当技术地基每季度崩塌一次:AI创业者的永恒追赶与“过时焦虑”
从Bengaluru对2000名未来创始人的告诫,到硅谷一线建设者关于“每季度重写架构”的感慨,一个共同的焦虑浮出水面:当技术的半衰期短到以月计算,我们究竟是在建造未来,还是在流沙上雕刻注定被潮水抹去的图案?
核心观点:AI模型能力的指数级跃迁,正在将技术创业从“构建护城河”的游戏,扭曲为一场“地基每季度崩塌一次”的永恒追赶,这不仅重塑了创业策略,更在根本上挑战着创新、价值积累乃至团队心理的可持续性。
如果你是一位AI领域的创业者,今天你引以为傲的、花了六个月精心搭建的系统架构,很可能在下一个季度发布的新模型面前,变得笨拙、低效甚至完全多余。这不是危言耸听,而是当前AI浪潮中最真实、也最令人窒息的常态。在Bengaluru,投资者告诉未来的创始人们,必须“身处信息流中”,实验最新的模型和开源项目;而在硅谷,一线的建设者们则在感叹,为了补偿模型局限性(如上下文窗口)而构建的复杂系统,如今已毫无用处,更简单的暴力计算反而成了更优解。这种技术迭代的速度,已经不再是线性增长,而是呈现出一种“范式跃迁”式的断层。它带来的第一个直接后果,是“第二波”或“第N波”创业者的机会窗口看似在扩大,但窗口的“保质期”却在急剧缩短。过去,一个“好点子”加上优秀的执行,可能足以让一家公司在几年内建立起竞争壁垒。但在AI时代,你的“优秀执行”所依赖的技术栈本身,可能在你完成产品市场匹配之前就已经过时了。你不再是和同一赛道的其他初创公司赛跑,而是在和位于旧金山、伦敦或北京的基础模型实验室的研发进度赛跑。他们的每一次突破,都可能让你的精巧设计从创新变成累赘。这就引出了一个深刻的悖论:一方面,所有人都被告知“执行就是一切”,快速构建和迭代的能力前所未有地重要;另一方面,你执行所基于的“技术地基”却极不稳定,你的快速构建很可能是在一个即将被废弃的平台上进行的。这种矛盾将创业者的决策置于巨大的不确定性之中。是应该押注当前最成熟但可能即将过时的技术栈,以求快速推出产品?还是应该不断追逐最新的、尚未稳定的技术前沿,冒着产品永远无法定型、团队疲于奔命的风险?这种“过时焦虑”正在重塑创业团队的构成与文化。投资者指出,年轻的、学习速度极快的创始人正占据优势。这不仅仅是因为他们精力充沛,更是因为在一个技术范式快速迁移的环境中,“经验”的价值可能被迅速折旧,甚至成为认知负担。一个对三年前Transformer架构了如指掌的资深工程师,可能不如一个刚毕业、但对最新多模态模型有直觉理解的年轻人更能适应新的构建方式。团队需要的是极强的“忘却”和“重学”能力,而非对某一套技术的深度积累。这种文化催生了所谓的“修补匠”文化,即出于好奇而非明确商业目的进行技术探索。这在快速变化期是产生新颖想法的源泉,但也可能导致项目缺乏持久的焦点和商业深度,永远停留在“有趣的原型”阶段。更深层次地看,这种技术迭代速度对“价值积累”构成了根本性挑战。传统的软件或互联网创业,其价值很大程度上体现在随着时间推移而不断加深的代码库、数据资产、用户网络和品牌认知上。这些是随时间复利增长的护城河。但在当前AI创业的某些领域,尤其是高度依赖模型能力的应用层,你的代码库可能因为底层模型的升级而需要大规模重构甚至重写;你的数据管道可能因为模型输入输出格式的变化而失效;你为特定模型弱点设计的复杂工作流,可能在新模型面前显得画蛇添足。那么,价值积累在哪里发生?或许会转移到一些更“硬”的层面:对垂直领域需求的深刻理解、独特的专有数据集、难以复制的用户体验设计、以及最重要的——一个能够持续适应、学习和重建的团队组织能力。但即便如此,这种积累也充满了变数。另一个不容忽视的维度是资本效率的扭曲。一方面,AI极大地提升了单个工程师的生产力,“一人可做百人团队一年前的工作”;但另一方面,为了追赶技术浪潮而进行的频繁架构重写,又吞噬了大量的开发资源。资本被同时要求支持极高的创新速度和极高的迭代成本,这可能导致只有那些资金极其充裕,或者商业模式能产生即时强劲现金流的公司,才能在这场马拉松式的冲刺中存活下来。这对于强调“精益创业”和“产品市场匹配”的传统硅谷智慧,无疑是一种冲击。当然,我们必须警惕将这一观察过度普遍化。并非所有AI应用都同样受制于基础模型的快速迭代。那些深度与具体业务流程结合、拥有强网络效应或独特数据闭环的应用,可能对底层模型的变迁有更强的缓冲。此外,开源生态的繁荣也在某种程度上对抗着这种“过时”风险,为开发者提供了更多可掌控、可延续的技术选择。但总体而言,技术地基的剧烈晃动,已经成为这个时代创业者必须直面的核心环境变量。它要求一种新的心智模式:不再追求一劳永逸的“完美架构”,而是拥抱“临时性”和“可废弃性”的设计哲学;将团队的适应能力和学习速度作为核心竞争力来建设;在追求速度的同时,为技术的必然过时预留心理和资源上的弹性。最终,这场永恒追赶的游戏,筛选出的可能不是那些拥有最炫酷创意的梦想家,也不是那些执行最一丝不苟的工匠,而是那些兼具海盗的敏捷与骆驼的耐力,能在流沙上不断搭建临时营地,并随时准备向下一个绿洲迁徙的探险者。这场竞赛的终点或许不是一座永恒的丰碑,而是一种在动态失衡中持续前行的能力本身。
如果把这个判断再往前推一步,真正重要的不是 RT by @paulg: What…、R to @karpathy: Som…、RT by @paulg: A new… 本身,而是它们共同暴露出的分配逻辑。 x 在同一轮里把注意力推向同一问题,通常意味着这个主题正在从圈层内部经验,转向更可共享的公共议题。 这也是为什么这种内容值得写成长文:短帖只负责提醒你“这里有事发生”,但只有长文才能把背景、代价、误判空间和后续影响放到同一张桌面上。 换句话说,AI模型能力的指数级跃迁,正在将技术创业从“构建护城河”的游戏,扭曲为一场“地基每季度崩塌一次”的永恒追赶,这不仅重塑了创业策略,更在根本上挑战着创新、价值积累乃至团队心理的可持续性。 之所以重要,不是因为它看上去新,而是因为它会重新定义用户接下来应该如何理解这一类内容。
参考来源
- RT by @paulg: What I told 2,000 future founders in Bengaluru today:
- 1/ We believe we are at the start of a second wave of Indian companies that will build world-class AI native products for the global market. Emergent and Giga are the model of the future.
- 2/ Just because a space seems crowded doesn't mean it's too late. Zepto, Emergent, Giga - none were first movers. Second mover advantage is real.
- 3/ In fact, a good formula for finding startup ideas is to look at ideas that are showing some promise and just execute them better. Execution is everything: if you're an exceptional engineer, and you can build and move faster than your competitors, you'll win.
- 4/ There is every reason to believe Indian teams can beat US teams building global products. The level of engineering talent here is on a whole different level, and that's the key input.
- 5/ In the AI era, the best founders are the ones building at the edge of what's technically possible. You need to be experimenting wth the latest models, the latest open source projects.
- 6/ Stay in the flow of information. Watch the right podcasts, follow the right people on X. With AI changing this fast, you need to know what the smartest builders are thinking.
- 7/ Most of the best startups don't come from someone explicitly trying to start a company. They start from someone building a project just for fun, or tinkering with a new technology because they are curious. India needs more of this "tinkering" culture - this is how you have novel ideas when technology is shifting quickly.
- 8/ Founders are getting younger. Aadit was 18 when he started Zepto. The Giga founders were 20 when they came to SF. Young people who can learn very fast have the advantage right now.
- 9/ The best founders are pushing AI coding to the max. You can now write 20K lines of code / day. One person can do the work that just a year ago would take a 100 person team. The best builders are taking advantage and building at Garry Tan speeds. - https://nitter.net/snowmaker/status/2045506195415535872#m
- R to @karpathy: Someone recently suggested to me that the reason OpenClaw moment was so big is because it's the first time a large group of non-technical people (who otherwise only knew AI as synonymous with ChatGPT as a website) experienced the latest agentic models. - https://nitter.net/karpathy/status/2042341482531864741#m
- RT by @paulg: A new paper in @Nature from David Reich, @aliakbari23 and colleagues breaks the conventional understanding of recent human evolution. The field believed that strong selection in the recent past (~10,000 years) was rare, with few exceptions like the lactase persistence locus. In this paper, the authors challenge that belief, showing that we weren't looking at the problem right.
- Previous studies that looked for evidence of selection using ancient DNA addressed the problem cross-sectionally, asking if allele frequencies differed across populations more than what one would expect based on genetic drift and migration. Most arrived at the conclusion that population structure primarily explained the observed differences. Here, the authors addressed the problem longitudinally, accounting for when ancient individuals lived by explicitly modeling time as a variable in the analysis. It turns out doing it this way dramatically increases power, increasing the number of genome-wide significant selection signals by 20-fold!
- Looking at why accounting for the time variable led to such dramatic changes in results, the authors find that previous studies missed so much because selection often happened not on new variants leading to dramatic sweeps (the conventional model: new variant -> selection -> increase in frequency) but on already existing variants driven by transient environmental pressures. Many of these variants underwent reversals, selected up when a pressure existed, then purged when it disappeared or the trade-off cost became dominant. A great example is the TYK2 variant, where an allele boosting immunity was selected for thousands of years because it protected against TB, then got purged as TB endemicity declined and the autoimmune cost took over.
- The scale of what they found is striking: hundreds of loci showing strong selection in the past 10,000 years with a median selection coefficient of ~0.86%. This number is pretty big in evolutionary terms, meaning allele frequencies have been shifting by ~1% per generation in a consistent direction. Previous selection scans found a maximum of 20 loci, and this one finds hundreds. That isn't an incremental change. It fundamentally reframes our understanding of how common strong selection has been in recent human history.
- Some of the most striking findings come from polygenic selection, where hundreds of small-effect alleles were pushed in the same direction simultaneously. Polygenic scores based on large-scale GWAS of today predict recent negative selection for traits like body fat, waist circumference and schizophrenia, and positive selection for others like cognitive traits. One important caveat is that GWAS phenotypes are measured in industrialized societies today, and how well they capture what was actually being selected in ancient environments is debatable.
- For me personally, these findings have direct implications for drug discovery. When using human genetics to find drug targets, we often fixate on the benefit and risk profiles of variants visible today. But we need to be aware that a variant's benefit:harm ratio might be environmentally contingent, and could reverse when the wrong environment manifests. An evolutionary understanding of a variant's association with traits is therefore essential.
- The same logic applies, perhaps even more urgently, to embryo selection. Selecting embryos based on polygenic traits is humans making permanent, heritable decisions for their offspring with a narrow view of today's environment. The ancient DNA record now shows that cost-benefit landscapes flip over time. So, an embryo carrying man-made selections is carrying those changes into an unpredictable future environment.
- The broader takeaway is that human evolution didn't freeze in the last 10,000 years. We just lacked the tools and datasets to see its movement. The current findings are based on European populations. I am curious to see these analyses extended to other populations too, like South Asian, East Asian and African populations, which might be holding more surprises to blow our minds.
- Akbari et al. Nature 2026
- https://www.nature.com/articles/s41586-026-10358-1 - https://nitter.net/doctorveera/status/2044679999450664967#m