Coding with LLMs in the summer of 2025 – an update(antirez.com)
541 points by antirez | 365 comments
Blog post by antirez (Redis creator) giving an update on how he uses frontier LLMs like Gemini 2.5 Pro and Claude for programming in summer 2025.
First screen, captured .
Looks similar
Scaling HNSWs(antirez.com)
198 points by cyndunlop | 42 comments
From where I left(antirez.com)
1111 points by tilt | 408 comments
Blog post by Redis creator antirez reflecting on leaving Redis about 4.4 years ago and announcing his return to the project.
Control the Ideas, Not the Code(antirez.com)
171 points by surprisetalk | 130 comments
Redis is open source again(antirez.com)
1808 points by antirez | 718 comments
Blog post by Redis creator antirez announcing Redis is switching to the AGPL license, making it open source again after the SSPL change, and explaining why.
Related stories
It's hard to write code for computers, but it's harder to write code for humans(erikbern.com)
429 points by imartin2k | 131 comments
Erik Bernhardsson's blog post arguing that writing code for humans, such as libraries, APIs and tools other developers use, is harder than writing code for computers.
The future of software development is software developers(codemanship.wordpress.com)
376 points by cdrnsf | 471 comments
A Codemanship blog post arguing that the future of software development still depends on human software developers.
The Eternal Sloptember(geohot.github.io)
347 points by razin | 280 comments
A blog post by George Hotz arguing that adopting AI coding agents in software development is a costly mistake because their output is subtly broken.
Coding expertise is going to collapse from AI reliance(larsfaye.com)
490 points by larsfaye | 479 comments
Blog essay by Lars Faye arguing that reliance on AI coding tools removes the friction needed to develop long-term programming expertise.
To be a better programmer, write little proofs in your head(the-nerve-blog.ghost.io)
414 points by mprast | 154 comments
Blog post by Matthew Prast on the Nerve blog arguing that programmers write better code by informally proving correctness in their heads as they work.
The new skill in AI is not prompting, it's context engineering(philschmid.de)
832 points by robotswantdata | 467 comments
Blog post by Philipp Schmid arguing that context engineering, supplying LLMs with the right information and tools, matters more than prompting for AI agents.