Hacker News

• EvolutionEngine— L1-L6 autonomous evolution loop • MemorySystem— declarative/episodic/procedural, weighted • NightlyReview— metacognition proto • CodeSandbox— self-modifying code • TokenBudget / LiveStatus / KnowledgeFusion Hunyuan API + Ollama. Runs. Growing.

Comments URL: https://news.ycombinator.com/item?id=48680473

Points: 1

# Comments: 0

WHIP (RFC 9725) is a standardised media ingress protocol: it serves to stream audio and video to a network server, and is supported by a number of media distribution systems. PipeWire is the currently fashionable multimedia framework for Linux, and almost all Linux applications are able to send audio to PipeWire, either natively or through PipeWire's emulation of the ALSA and PulseAudio APIs.

Pw-whip is a bridge between PipeWire and WHIP: it enables every application that can speak to PipeWire to stream its audio to any compliant WHIP server.

Comments URL: https://news.ycombinator.com/item?id=48680445

Points: 1

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=48680434

Points: 2

# Comments: 1

Article URL: https://morethanmoore.substack.com/p/ibms-announces-07nm-process-node

Comments URL: https://news.ycombinator.com/item?id=48680424

Points: 2

# Comments: 0

Article URL: https://rslmedia.org/

Comments URL: https://news.ycombinator.com/item?id=48680410

Points: 1

# Comments: 0

Article URL: https://gchandbook.org/

Comments URL: https://news.ycombinator.com/item?id=48680370

Points: 2

# Comments: 1

Article URL: https://www.nextgig.rocks/dash/how-ai-changes-jobs

Comments URL: https://news.ycombinator.com/item?id=48680358

Points: 2

# Comments: 0

I don't mean migration in the sense of switching databases or rewriting in another language. I mean that a codebase rots if nobody maintains it. Deprecations, warnings, upstream changes — each is cheap to handle the moment it appears, often a 10-minute fix (let's say 'in average'). But plenty of teams never catch them. No real CI/CD, no culture of reading changelogs or acting on warnings. So it piles up silently, and then at some point — usually when an infra or security team shows up with tickets — the whole accumulated pile lands on one person at once. Often a new hire or a junior who's never seen the code, with no record of why any of it is the way it is beyond git blame, a stale changelog, and a few dead chat threads. What I think gets underestimated is that clearing it all at once costs far more than the sum of the small fixes would have. The problems tangle into each other, and the context that would let you separate them is already gone. So I'm trying to learn from people who've been dropped into this. What did you actually reach for, and what worked — tests, diffing output before/after, shadowing prod traffic, or just running it and hoping? Did anyone try LLM agents, and where did they genuinely help versus confidently make things worse? (I know of an Angular case where the agent kept patching a function it assumed was the problem, and after a couple of failed runs invented its own workaround — when the correct approach was in the docs the whole time). Just time spending. If you can ballpark it: how much worse was all-at-once versus incremental — 3x, 10x? And one thing I keep wondering: when you were reconstructing a system like this, what were you missing more — a description of what the code does, or of what someone meant it to do? Those feel like two different problems.

Comments URL: https://news.ycombinator.com/item?id=48680354

Points: 1

# Comments: 0

Article URL: https://joshumax.github.io/elma-web/

Comments URL: https://news.ycombinator.com/item?id=48680330

Points: 1

# Comments: 0

Article URL: https://github.com/TangibleResearch/HoprLabs

Comments URL: https://news.ycombinator.com/item?id=48680309

Points: 2

# Comments: 0

Article URL: https://finance.yahoo.com/technology/ai/articles/oracle-workforce-shrinks-13-204431510.html

Comments URL: https://news.ycombinator.com/item?id=48680283

Points: 1

# Comments: 0

Article URL: https://www.autocar.co.uk/car-news/electric-cars/ford-could-bring-f1-inspired-skunkworks-evs-europe

Comments URL: https://news.ycombinator.com/item?id=48680278

Points: 2

# Comments: 0

There is an adversarial relationship between developers and big model labs.

Model labs charged developers higher API prices to subsidize their own agent harness offerings. Think Anthropic charging 5x higher Claude API prices to subsidize consumer subscriptions. So Cursor in a way was subsidizing their own direct competitor.

DeepSeek V4 Flash totally inverted this relationship. Now you have a model that beats even Sonnet in some benchmarks and is totally opensourced. Now inference providers are racing to the bottom to optimize and give cheaper hosting. Every player with a non-SOTA is now racing to swap over to stop paying the big model lab tax, even Microsoft is switching Copilot to use DeepSeek.

On switching over to Deepseek: - we noticed over a 100x cost decrease while similar or better performance then Gemini 3 Flash - insane saving from the cached input tokens: $0.002/1 Million tokens - both DeepSeek Flash and GLM 5.2 are text-only models, so clearly multimodal training is not worth the additional cost. Language is just a much more efficient sparse representation of the world/reasoning than vision - we had a early bet on a text-only web agent harness, and now with DeepSeek this results in a unique cost advantages. - we rewrote our harness as a callable DSL library that a model can generate code to execute on. DeepSeek has proven phenomenal on code generation to drive an agent harness. - I would highly recommend everyone to rewrite their harness to be text-only and callable via executable code

Comments URL: https://news.ycombinator.com/item?id=48680260

Points: 3

# Comments: 0

Article URL: https://en.wikipedia.org/wiki/Om_Malik

Comments URL: https://news.ycombinator.com/item?id=48680251

Points: 1

# Comments: 0

Article URL: https://capolicylab.org/california-ai-unemployment-tracker/

Comments URL: https://news.ycombinator.com/item?id=48680242

Points: 1

# Comments: 0

Article URL: https://proofsandintuitions.net/2026/06/24/liveness-proofs-in-veil-part-1/

Comments URL: https://news.ycombinator.com/item?id=48680234

Points: 1

# Comments: 0

Article URL: https://www.bleepingcomputer.com/news/security/new-macos-malware-embeds-fake-errors-to-confuse-ai-analysis-tools/

Comments URL: https://news.ycombinator.com/item?id=48680232

Points: 1

# Comments: 0

Article URL: https://datascienceweekly.substack.com/p/data-science-weekly-issue-657

Comments URL: https://news.ycombinator.com/item?id=48680231

Points: 1

# Comments: 0

Article URL: https://charlottekupewasserphd.substack.com/p/the-sunscreen-result-no-one-wants

Comments URL: https://news.ycombinator.com/item?id=48680226

Points: 3

# Comments: 1

Article URL: https://codeberg.org/slaubenberger/Powercode

Comments URL: https://news.ycombinator.com/item?id=48680212

Points: 3

# Comments: 0