quinncom

If I want to onboard a client to Cloudflare, I have to ask them to create an account and then invite me, which is a lot of friction for non-technical people.

A “create account” button accessible to me would be so much better. Then, I create the account and invite the client to join as owner.

Gmail will block messages that fail SPF/DMARC alignment unless the forwarding mail server supports SRS.

Similarly, `Go Map!!` is an iOS app that makes editing OSM data easy.

Adding missing features is one of my favorite things to do while traveling, and feels like a way of giving back (“take only photos, leave only GIS traces”?)

> it automatically falls back to Claude Opus 4.8

I wonder how much of the time people will just get Opus 4.8 at 2× the cost.

Don’t presume this study has anything to do with programming. They measured an agent’s ability to search long conversations, not code.

> We evaluate on a 116-question representative subset of the LongMemEval benchmark (Wu et al., 2025), which tests an agent’s ability to answer questions over long conversations spanning multiple sessions.

Honestly, when I see headlines like this I just scroll down to the Kagi comment and upvote it.

I don’t use Slack either. What about solo indie founders who don’t use “team communication”?

Plaid is criticized because it’s a public-facing mechanism for third-party access into your finances, but many companies already have access without you knowing. In the US, many banks share nonpublic info such as transactions with retailers, marketers, government agencies, and others. They’re allowed to do so under the Gramm-Leach-Bliley Act. Report from the GOA:

https://www.gao.gov/products/gao-21-36

The article doesn't really get into the details. Does it analyze the user agent and compare it to a list of known bot user agents? What about all the bots that spoof user agent values – does it do something special to detect those?

It must have been so fun to be Benjamin Franklin. He installed an electric bell in-line on his first lightning rods so that this increase in electrical potential would cause the bell to ring, signaling that the danger for lightning was increased.

You can experience this voltage potential firsthand: take a friend to a hill or somewhere where high‑voltage power lines are nearer to the ground. One person, wearing rubber-soled shoes, stands tall with an arm in the air. The other squats down with both hands on the ground. The standing person uses the non-raised hand to gently touch the sensitive skin of the other person (ear lobe, lips), and they can feel an electric arc.

Kagi’s small web app is fun: https://kagi.com/smallweb/

Probably it did, but just thought, “I’m saving this one just for me”

Obviously I’m virtue signaling, and I hope instilling a feeling of shame in people who support businesses that contribute to climate change.

But more than that, the emissions generated by the Colossus data centers are far worse than typical combined-cycle gas plants or data centers that buy renewable: these turbines emit NOx, fine particulates, carbon monoxide, and formaldehyde into a population-dense area.

I thought people knew about this already. Post from last year: https://simonwillison.net/2025/Jun/12/xai-data-center/

One of the reasons I refuse to use xAI’s models is because of the outsized negative environmental impacts of the methane gas turbines.

Now I have to avoid Claude too.

I’m getting a “Forecast API error: 429 - Too many concurrent requests” error.

Do you know how much it affects your deep sleep duration?

People who drink caffeine at night may claim to be able to sleep still, but they will find that deep sleep stages are shorter, which is significant because it may be the most important type of sleep.

Mexico already has “universal healthcare.” The public hospitals are so bad and chaotic that most people who can afford to pay private insurance so they can go to private hospitals.

The article doesn't state explicitly, but I guess this new decree changes the qualifying rules. For example, that even if you have private insurance, you can still access public healthcare facilities.

I don't see how this is going to work unless they also improve the resources to the public facilities.

You can try McFly [1] and Television [2]. I still prefer fzf.

[1] https://github.com/cantino/mcfly

[2] https://github.com/alexpasmantier/television

“We found that the phenomenon described in these posts—cognitive exhaustion from intensive oversight of AI agents—is both real and significant. We call it “AI brain fry,” which we define as mental fatigue from excessive use or oversight of AI tools beyond one’s cognitive capacity.”

https://hbr.org/2026/03/when-using-ai-leads-to-brain-fry

I've never experienced a miracle, but I'm surrounded by people who claim to have seen one or know somebody who did. I'm still waiting for mine.

I met with a supposedly realized Buddhist master in a monastery in Nepal and asked him if he had ever had a supernatural experience (Buddhist cosmology has many stories about enlightened people flying, walking through walls, etc). At first he had difficulty understanding the question (the translator seemed to have difficulty finding the right words). Finally he replied with a blunt “No.” But then amended that with the inconclusive statement, “If a supernatural event occurred, by it existing, it would immediately cease to be supernatural because there would be some explanation for it.”

If I had been tethering to mobile hotspot at the time it would have instantly used 500 pesos of data. That’s 3x my monthly electric bill.

I accidentally clicked the Claude Cowork button inside the Claude desktop app. I never used it. I didn't notice anything at the time, but a week later I discovered the huge VM file on my disk.

It would be really nice to ask the user, “Are you sure you want to use Cowork, it will download and install a huge VM on your disk.”

Happy is buggy af and is in the middle of a rewrite (see its Discord).

A fork named Happier looks promising, but is alpha-stage and is also a mystery-meat vibe-coded security roulette.

The README claims “Full feature parity with pi,” but I presume pz does not support pi’s extension/package ecosystem (because they’re all writted in TS and so would require bundling node/bun) – is that correct? One of the highlights of pi is its extensibility; if that’s not possible with pz, it should be clearly stated as a goal/nongoal.

I just learned yesterday that ChatGPT (and maybe others) can’t connect to a MCP running on localhost; it needs an endpoint on the public internet. (I guess because the request comes from OpenAI servers?)

I’d rather not expose a private MCP to the public, so ContextVM sounds like a step in the right direction. But I’m confused about how it is called: doesn’t OpenAI’s servers still need you to provide a public endpoint with a domain name and TLS? Or does it use a Nostr API?

I like Readeck – https://codeberg.org/readeck/readeck

Open source. Self hosted or managed. Native iOS and Android apps.

Its Content Scripts feature allows custom JS scripts that transform saved content, which could be used to do URL rewriting.

The 2025 Stack Overflow Developer Survey asked participants to identify dev tools they use (“Desired”) and want to use again (“Admired”). Dividing these scores calculates a “underrated score” which reveals which tools may be hidden gems.

I've compiled a list using this method, filtering for tools admired by >60%, and used by <20% of developers, then sorted by “underrated”.

The previous 2024 list is available here: https://news.ycombinator.com/item?id=41090759

In 2025 there were a total of 12 tools with an admired score >70%. In 2024 there were 41. Are we admiring our tools less? Or did we stop caring because AI is touching the tools instead of us?

Although I rarely hit my limit in my $20 a month Codex plan, I can imagine this would be very useful.

The issue I have more often is that I will start a conversation in ChatGPT, and realize an hour later that I needed all that context to be in Codex, so I’ll generally ask ChatGPT to give me a summary of all facts and a copy‑paste prompt for Codex. But maybe there is a way to extract the more useful content from a chat UI to an agent UI.

Update: I switched to Qwen3 VL 2B (`qwen3-vl-2b-instruct-mlx@bf16`) which is 2.5× faster than 4B (11s vs 18s per screenshot) and my meager M1 Pro is able to keep up without the fans spinning 100% of the time.

I've got it installed with Qwen3-VL-4B running in LM Studio on my MBP M1 Pro. (Yes, the fans are running.) GLM-OCR didn't work because it returns all text on the screen, despite the instructions asking only for a summary.

Screenshots are summarized in ~28 seconds. Here's the last one:

> "The user switched to the Hacker News tab, displaying item 47049307 with a “Gave Claude photographic memory for $0.0002/screenshot” headline. The chat now shows “Sonnet 4.6” and a message asking “What have I been doing in the past 10 minutes?” profile, replacing prior Signal content. The satellite map background remains unchanged."

The satellite map background remains unchanged message appears in every summary (my desktop background is a random Google Maps satellite image that rotates every hour).

I would like to experiment with custom model instructions – for example, to ignore desktop background images.

Earlier in my testing it was sending screenshots for both of my displays at the same time, which was much slower, but now it's only sending screenshots of my main screen. Does MemoryLane only send screenshots for displays that have active windows?

Here's the first test of the MCP server in Claude – https://ss.strco.de/SCR-20260217-onbp.png – it works!