Hacker News

Article URL: https://theconversation.com/what-the-sudden-demise-of-the-uks-department-of-science-means-for-the-future-of-research-288121

Comments URL: https://news.ycombinator.com/item?id=49027398

Points: 1

# Comments: 0

Article URL: https://queue.acm.org/detail.cfm?id=3335594

Comments URL: https://news.ycombinator.com/item?id=49027390

Points: 1

# Comments: 0

Article URL: https://openworker.com/

Comments URL: https://news.ycombinator.com/item?id=49027382

Points: 1

# Comments: 0

Article URL: https://www.popsci.com/environment/why-dogs-kick-ground-after-potty/

Comments URL: https://news.ycombinator.com/item?id=49027366

Points: 1

# Comments: 0

Article URL: https://easyoptouts.com/guides/apple-hide-my-email-was-leaking-email-addresses

Comments URL: https://news.ycombinator.com/item?id=49027365

Points: 1

# Comments: 0

Article URL: https://www.economist.com/insider/the-insider/an-interview-with-elon-musk

Comments URL: https://news.ycombinator.com/item?id=49027360

Points: 2

# Comments: 1

Article URL: https://github.com/tomlin7/biscuit

Comments URL: https://news.ycombinator.com/item?id=49027355

Points: 1

# Comments: 0

Article URL: https://www.beyonddream.me/post-13/

Comments URL: https://news.ycombinator.com/item?id=49027339

Points: 1

# Comments: 0

Article URL: https://www.flightradar24.com/AIB35LR/40ce0e1e

Comments URL: https://news.ycombinator.com/item?id=49027313

Points: 1

# Comments: 0

Hi HN,

I'm building CobaltCode, a platform for running coding agents inside persistent development environments.

Basically I was fed up with git worktrees and having to run everything locally, usually one at a time so built CobaltCode.ai. Each task gets an separate vm with its own repository checkout, dependencies, running services, agent session, previews, and persistent state. It can also run your app inside the vm so you can preview different features in parallel.

You can leave a task, resume it later, or save the computer as a reusable starting point. The agent is a full-fledged Codex that runs without limits in the sandbox and can run commands, modify files, start applications, and expose browser previews from inside the isolated environment.

It uses your OpenAI subscription so you don't pay for tokens in CobaltCode and the product is currently free while I'm trying to figure out how useful it is.

CobaltCode currently supports OpenAI Codex in PROD and I am also adding Cursor Agent, Claude Code, GitHub Copilot CLI, OpenCode and Pi soon.

For repository providers the support is limited to GitHub and Azure DevOps for now. Credentials are injected only for the active operation and excluded from saved computer state.

It is still early, and I would especially appreciate feedback on:

What would make this useful for your own development workflow What features you think may be useful to add Any bugs or mistakes

Demo: https://youtu.be/1yyhj5wYyvA

I also submitted it for OpenAI Build Week here, I'd appreaciate the support: https://devpost.com/software/cobalt-code

Happy to answer technical questions or help in anyway

Vlad

Comments URL: https://news.ycombinator.com/item?id=49027309

Points: 1

# Comments: 0

Article URL: https://flux3.studio

Comments URL: https://news.ycombinator.com/item?id=49027308

Points: 1

# Comments: 1

Article URL: https://joshkaramuth.com/blog/simplicity-doesnt-sell/

Comments URL: https://news.ycombinator.com/item?id=49027284

Points: 2

# Comments: 2

Hey HN, Open artifact is an easy way to view your docs, html artifacts and collaborate with others.

I like to keep my stack llm agnostic. My default way is to read docs via markdown and visualize reports via html. But sharing it with colleagues and keeping track of it was a big pain. I like claude artifacts but I don't like to get tied to a single provider. So, I built open artifact.

Open artifact is free. You can host it yourself too. Hope you find it useful.

Comments URL: https://news.ycombinator.com/item?id=49027280

Points: 1

# Comments: 0

Article URL: https://api-first-world.com/

Comments URL: https://news.ycombinator.com/item?id=49027278

Points: 1

# Comments: 1

Article URL: https://www.foreignaffairs.com/china/chinas-moment-weakness

Comments URL: https://news.ycombinator.com/item?id=49027269

Points: 1

# Comments: 0

I’ve been building Echo (https://echo.tracerml.ai/), an experiment in making one AI system out of a pool of open-weight models rather than choosing a single model and using it for every task.

It started with a simple experiment. I took a group of models, including GLM-5.2, Kimi K2.7 and others, and ran them on the same evaluations. Then I measured what would happen if, for each problem, you somehow knew in advance which models would be useful and how their outputs should be combined.

That hypothetical system performed substantially better than any individual model in the pool. Of course, it is not something you can actually deploy because it relies on knowing which decisions were good after seeing the result. Echo is my attempt to recover some of that advantage without having that information in advance.

For each request, Echo decides how much computation to allocate, which models should participate, and how their work should be combined. Some prompts may only need a relatively small amount of inference, while others benefit from multiple models working on different parts of the problem.

One thing that surprised me while building it was how complementary the models are. A model that is clearly weaker overall can still be extremely useful on particular problems or as part of a combination.

On my first evaluation mix, Echo consistently performed better than the best individual model in its pool. It also reached roughly the same aggregate result as Fable, which I used as one of the stronger comparison systems, at around one third of the inference cost.

There are still some cases where Echo makes the wrong allocation or combination decision. I’m currently spending a lot of time understanding those failures, as well as testing whether the same approach holds up on coding and agentic tasks where measuring the quality of each decision becomes much harder.

I built a chat interface (echo.tracerml.ai) and an OpenAI-compatible API (https://echo.tracerml.ai/docs/api) so the system can be tested outside the evaluation setup.

Here is a short/high level video on how it works: https://youtu.be/lJFJSvOdXhg

I wrote up the evaluation methodology, individual model results, costs and current limitations here: https://echo.tracerml.ai/eval

I would love for you to try it! Especially if you hit any weird failure cases or places where the allocation looks unintuitive.

Comments URL: https://news.ycombinator.com/item?id=49026810

Points: 1

# Comments: 0

Article URL: https://www.cnn.com/2026/07/23/politics/republicans-capitalism-socialism-poll

Comments URL: https://news.ycombinator.com/item?id=49026787

Points: 2

# Comments: 0

Hi guys,

Just needed a good way to quickly record a beautiful product demo on Windows with automatic zoom, cursor highlights, background etc.

Tried a couple of products but they pissed me off (heavy, slow, expensive, didn't let you use all the features).

So I built this in anger. It's simple, lightweight, free (and always will be), and creates beautiful videos.

Grateful for any issues or PRs.

Thanks, Chris

Comments URL: https://news.ycombinator.com/item?id=49026781

Points: 1

# Comments: 0

Article URL: https://www.msn.com/en-us/news/other/media-silence-as-kushner-s-2b-tie-to-saudis-slips-under-cover-of-trump-deal-analyst/ar-AA28xRF6

Comments URL: https://news.ycombinator.com/item?id=49026757

Points: 2

# Comments: 0

Article URL: https://www.nrl.navy.mil/Media/News/Article/4551871/robotic-servicing-of-geosynchronous-satellites-launches-into-orbit/

Comments URL: https://news.ycombinator.com/item?id=49026755

Points: 2

# Comments: 0