My hypothesis is that there is a new opportunity for Extensible Software on the web . LLMs radically lower the cost of authoring extensions, and modern sandbox primitives lower the deployment cost and provide good security boundaries. We can build our app as a solid, accountable core, and allow users to safely extend it in many directions by having LLMs fill in the missing pieces. We can give our users super powers. — Jeremy Morrell , Extensible Software in the age of LLMs Tags: sandboxing , llms , ai , generative-ai
Last week I recorded an episode of the Talking Postgres podcast with Claire Giordano on the subject of "How AI is changing software development". We had a really great conversation. Here are a couple of my highlights from a lightly edited transcript (prompt to Claude: "very minor edits to remove disfluencies"). This is the latest version of an argument I've been trying to build about why sometimes it does make sense to talk about lines of code as an indicator of productivity with coding agents, at 35:01 : A lot of people will tell you it makes no sense to measure productivity in lines of code. I’d actually disagree, because there’s a hard limit. In the before-times, a software engineer could produce a few hundred lines of production-ready code per day — and 200 lines of working, debugged, production-level code is an incredibly good day. Most days you’d produce 50 or 60. If agents let you produce a thousand lines of debugged code, that really is a very meaningful improvement — as long as the code is the same quality: maintainable, tested, all of that. You can get to that point with agents, but it takes a huge amount of skill and knowledge and experience. That’s what senior engineers are made of. I can do way more work as a single engineer than I could without agents. So you could argue, why should a company have more than one engineer? Beyond the obvious bus factor thing — a team of one is a very badly designed team — the answer is that the new limiting factor is cognitive capacity. I can churn out code a hundred times faster. I don’t have the cognitive capacity to stay on top of 100 times the amount of code. So you still need a team of engineers, so you can load balance that cognitive capacity across the team. And this section on conceptual integrity at 46:03 , which Claire equated to the Winchester Mystery House ! Simon : There’s a concept in The Mythical Man-Month — conceptual integrity — where well-designed software has an integrity to it: there are no surprises in it, it covers exactly the right domain of things, everything fits together and makes sense. That’s so much harder with coding agents, where you can have an idea for a feature, run a prompt, and five minuteslater you’ve got the feature. Your software grows little weird bumps in funny different directions. Claire : You know my analogy for that? The Winchester Mystery House. Simon : It’s got 140 rooms, because the woman who built it was the widow of the guy who invented the Winchester rifle, and her psychic told her she’d be haunted by the ghosts of everyone killed with that rifle unless she kept building the house forever. So for 40 years she kept adding new rooms. That’s exactly the problem with coding agents and software: it’s very easy to keep adding new rooms, because the cost of adding those rooms is so much cheaper. What you end up with is something where the conceptual integrity falls apart — and then it’s harder to make decisions about it. It all keeps coming back to discipline. It used to be that the discipline was enforced on you by the amount of time it took. You’d come up with an idea for a crazy feature and think “yeah, but that would take me a week — I cannot justify that, so I’ll forget about it.” If it takes an hour, it’s so much easier to justify. (Side-note: the Wikipedia article includes credible sources that dispute the story about the psychic.) Tags: ai , generative-ai , llms , podcast-appearances , coding-agents
What's Changed Add a model metadata cache to reduce Ollama’s per-request overhead New Contributors @gaugarg-nv made their first contribution in #17752 Full Changelog : v0.32.14...v0.32.15-rc1
What's Changed New desktop onboarding flow on first launch Caches resolved model metadata between requests, cutting time-to-first-token by roughly half (TTFT dropped from ~995 ms to ~524 ms in benchmarks) Fixes a bug where chat and generate could wedge after a mid-stream parser error Qwen 3.8 system messages are now normalized so non-leading system messages are handled consistently MLX and llama.cpp dependency updates New Contributors @gaugarg-nv made their first contribution in #17752 Full Changelog : v0.32.14...v0.32.15
HoverAir drones always have intriguing gimmicks. This one folds flat to fit in your pocket. This one can land on water. Another can charge inside its carrying case. But the brand's latest trick might be its riskiest: it's attempting to sneak a drone past the FCC. In December 2025, the US government banned future foreign […]
Six passengers — five US citizens and Ecuador's intel boss — all died in a remote area of Kenya on Wednesday when their helicopter crashed. Aviation accidents in Kenya have increased as tourism expands in the country.
Something of a trend has emerged this year, with the major AI labs going all-out to tell the world how The post “The opening stages of OpenAI’s unraveling”: OpenAI slows model training — not everyone is buying the explanation appeared first on The New Stack .
SpaceX was reportedly in talks to buy AI coding startup Cognition. SpaceX has already acquired Cursor as it races to catch up to rivals like OpenAI and Anthropic in enterprise AI.
Developers & Open Source · langchain-ai/langchain Releases
Changes since langchain-openai==1.5.2 release(openai): 1.6.0 ( #39762 ) feat(core): add standard model exception types ( #39538 ) fix(openai): raise clear error on unexpected response type in _create_chat_result ( #39731 )
M-151, ChromeOS version 16733.54.0 (Browser version 151.0.7922.168) has rolled out to ChromeOS devices on the Stable channel. If you find new issues, please let us know one of the following ways: File a bug Visit our ChromeOS communities General: Chromebook Help Community Beta Specific: ChromeOS Beta Help Community Report an issue or send feedback on Chrome Interested in switching channels? Find out how. Andy Wu Google ChromeOS
US President Donald Trump's administration has ramped up its pressure on the International Criminal Court (ICC), accusing it of being "politicized." The EU, France, Germany, Spain and Japan have defended the court.
A Trump-aligned think tank has ties to a highly unusual Census Bureau report that the president is using to renew false claims of widespread voting by non-U.S. citizens in 2020, NPR has learned.