Hacker News

Article URL: https://wellfound.com/jobs/4377171-ai-product-manager-vision-ai

Comments URL: https://news.ycombinator.com/item?id=48874077

Points: 1

# Comments: 0

Article URL: https://open-sandbox.ai/

Comments URL: https://news.ycombinator.com/item?id=48874053

Points: 1

# Comments: 0

I've been observing this for a while, where very basic queries about atproto stuff doesn't show up. But yesterday I found a query that makes it VERY obvious: "list of public atproto relays". Here's DuckDuckGo:

1. https://firehose.directory

2. https://atproto.at/relays

3. https://atproto.wiki/en/wiki/reference/core-architecture/relay

4. https://pulsar.feeds.blue

5. https://leaflet.pub/12022731-ae4f-4a13-9f7a-5738b7a83c2e

Of those results, Google only has 3, the only one on the list that... doesn't have a list of public atproto relays. None of the other sites are present anywhere. Trying not to assume malice instead of incompetence here, but it's really ironic that one of the ecosystems with the strongest ties to the open web, with users creating dozens of new websites every week, isn't getting indexed.

Comments URL: https://news.ycombinator.com/item?id=48874046

Points: 7

# Comments: 0

Article URL: https://paulgraham.com/thist.html

Comments URL: https://news.ycombinator.com/item?id=48874020

Points: 3

# Comments: 0

Article URL: https://www.indiegogo.com/en/projects/miruns/miruns#/section/project-story

Comments URL: https://news.ycombinator.com/item?id=48873988

Points: 1

# Comments: 0

Article URL: https://www.nytimes.com/2026/07/10/travel/barcelona-overtourism-jose-antonio-donaire.html

Comments URL: https://news.ycombinator.com/item?id=48873986

Points: 1

# Comments: 0

Article URL: https://www.wsj.com/tech/ai/alex-karp-is-saying-what-every-angry-ceo-is-thinking-about-ai-7f5f7c0c

Comments URL: https://news.ycombinator.com/item?id=48873978

Points: 4

# Comments: 0

Article URL: https://github.com/MrWizard94-Compile/repoforge

Comments URL: https://news.ycombinator.com/item?id=48873971

Points: 1

# Comments: 0

Article URL: https://www.nishantjani.com/blog/error-log-pattern-analysis-is-hard/

Comments URL: https://news.ycombinator.com/item?id=48873965

Points: 2

# Comments: 0

Article URL: https://better-prayer.com

Comments URL: https://news.ycombinator.com/item?id=48873962

Points: 1

# Comments: 1

I found this model "lfm2.5-thinking" which is "designed for on-device deployment" and is really tiny: just 1.2b params (~700 MB)

My first and very short interaction was so terrible that I felt no need to continue, but not in the way you think:

Here is the extremely brief transcript:

>>> hey Thinking... Okay, let's see what the user wrote here. They just said "heat". Hmm, maybe they want a response to that? ... First "heat" could be a standalone message... You saw that? It misread my "hey" as "heat", and kept going like this throughout the entire thinking process.

I thought I know what to expect from tiny local models like this.

But I did not expect it to be this bad. How would this be useful for anything local if it cannot even read a three letter-word properly?

Is this just lfm2.5 being terrible, or is this level of error a common trait in this model size range. Curious to hear from other folks' experiences.

Comments URL: https://news.ycombinator.com/item?id=48873957

Points: 1

# Comments: 0

Article URL: https://evanhahn.com/prefer-strict-tables-in-sqlite/

Comments URL: https://news.ycombinator.com/item?id=48873940

Points: 2

# Comments: 0

Before you say it's impossible, please go try.

---

CIQA, an analytic Quantum Error Correction code, is now freely accessible on GitHub alongside CIQS, the 'million-qubit compiler'.

Here's a brief overview of the stack:

1. CIQS - An analytic circuit transpilation pipeline (no heuristics, no tunable parameters). It passed the full IBM Benchpress transpilation suite (892/892 tests) in 75 minutes on older hardware, while Qiskit took 17+ hours. It scales linearly to 1M+ qubits on the same harness (that is one million and above).

2. CIQA - An analytic 1:5 QEC that enables full active computation and complete Pauli correction at depth on existing hardware. On real quantum hardware, it delivered a mean fidelity improvement of up to +0.832 over bare qubits. On the same hardware, it successfully ran the full Hayden-Preskill black hole circuit, preventing early decoherence, and enabling the first observation of black hole evaporation past the Page time.

CIQS and CIQA were validated on IBM Heron r2 during real, deep computation runs. Both natively handle quDits, and both are hardware-agnostic.

---

CIQA is added to the CIQS GitHub repository as part of the full pipeline. CIQA can integrate any stack, but when paired with the CIQS compiler, the pipeline automatically isolates the CIQA encoding prefix (no extra coding needed).

All benchmarks are documented and public, alongside published papers. All links are in the GitHub README.

---

## Note on CIQA's overhead

5 physical qubits from the [[5,1,3]] perfect quantum code layout + 2 dedicated ancilla qudits per logical block (one per channel) for syndrome extraction. For a 156-physical-qubit QPU: 156/7 ≈ 22.

For 156 physical qubits, CIQA delivers 22 fully protected logical qubits allowing deep computation on real QPU, today.

---

What experiment will you attempt first with it? Feedback is welcome.

Comments URL: https://news.ycombinator.com/item?id=48873939

Points: 3

# Comments: 0

Article URL: https://www.wired.com/story/security-news-this-week-ai-found-a-root-bug-in-linux-that-everyone-missed-for-15-years/

Comments URL: https://news.ycombinator.com/item?id=48873669

Points: 1

# Comments: 0

Article URL: https://arxiv.org/abs/2606.01736

Comments URL: https://news.ycombinator.com/item?id=48873658

Points: 1

# Comments: 1

Article URL: https://arstechnica.com/science/2026/07/a-jupiter-size-planet-that-escaped-its-stars-death/

Comments URL: https://news.ycombinator.com/item?id=48873626

Points: 1

# Comments: 0

Article URL: https://www.nytimes.com/2026/07/10/us/politics/ai-terrorism-boko-haram-nigeria.html

Comments URL: https://news.ycombinator.com/item?id=48873622

Points: 1

# Comments: 0

Article URL: https://blog.grandimam.com/posts/how-hacker-rank-scores-engineers/

Comments URL: https://news.ycombinator.com/item?id=48873620

Points: 1

# Comments: 0

Article URL: https://github.com/testedmedia/seo-command-center

Comments URL: https://news.ycombinator.com/item?id=48873583

Points: 2

# Comments: 0

Hi HN, Codex and Claude are pretty good at (re)searching things on the web these days, but the open coding agents (OpenCode, pi coding agent and friends) don't have access to the labs' proprietary search APIs. I wasn't happy with this state of affairs, and wanted a truly open source version that was portable and harness independent.

I'd previously implemented agentic web search using SearxNG for treechat.com with good results, so that was my first choice. The problem is that SearxNG expects to run as a standalone python service, which is a lot of overhead and infra to deal with just to give your agent reasonable web search functionality.

So I built a standalone CLI that embeds SearxNG as a library and exposes its search tools as a CLI and over MCP without having to spin up any extra services. It also has built-in tools for retrieving and markdownifying arbitrary URLs, and is agent friendly with skills and agent onboarding info built directly into the CLI. Together with the search functionality, this gives an agent everything it needs to competently search the web so long as it can find the `searxng` binary on PATH.

Getting all that to work was actually quite tricky but works reliably: I first have CI build a wheel of upstream SearxNG, then my CLI uses that wheel as a dep, and then I package the entire thing into an easy to deploy single-file binary using pybin[1] to avoid issues with pyinstaller.

The result is a portable easy to use tool that gives agents like Hermes, Openclaw, pi coding agent, OpenCode, or whatever agent you prefer the ability to reliably search the web.

[1]: https://github.com/nikvdp/pybin

Comments URL: https://news.ycombinator.com/item?id=48873578

Points: 1

# Comments: 0