Hacker News: o10449366

New comment by o10449366 in "Claude.ai and API unavailable [fixed]"

o10449366 — Thu, 30 Apr 2026 01:33:46 +0000

I've been on the $200 plan for 3 months, but this will be my last month. I got great use out of 4.5 for a while, but 4.6 felt like a half step back (conflated with all the random hidden config changes during it), and 4.7 is genuinely terrible.

It's impossible to tell these days whether 4.7 is stuck because it's thinking and Anthropic suppressed all output (seriously, 4.7 will just start making changes without explaining any reasoning - how is that an upgrade?) or because the underlying infrastructure is having issues.

4.5 -> 4.7 feels like going from working with a coach-able, junior engineer that does well with clear guidance to working with a cocky mid-level that will spend too long on pointless tangents and make confidently incorrect changes without any discussion.

New comment by o10449366 in "GitHub Copilot code review will start consuming GitHub Actions minutes"

o10449366 — Tue, 28 Apr 2026 21:26:53 +0000

Cache create is 202,746,985 and cache read is 11,998,411,722 from claude-code-monitor

New comment by o10449366 in "OpenAI models coming to Amazon Bedrock: Interview with OpenAI and AWS CEOs"

o10449366 — Tue, 28 Apr 2026 21:11:50 +0000

Lol, spinning up swat teams because someone high up decides "drop everything this is my pet priority now" is politicking. It looks good for the leaders, meanwhile its the engineers pulling the all nighters and dealing with having to maintain systems that are operationally compromised from day 0 because there's no proper planning/scoping involved other than "Big Man says this needs to be done in 2 weeks"

New comment by o10449366 in "GitHub Copilot code review will start consuming GitHub Actions minutes"

o10449366 — Tue, 28 Apr 2026 15:41:39 +0000

Yeah, I'm sure the numbers are a bit inflated compared to API, but with my Claude $200/month subscription I've supposedly consumed 12,160,410,828 tokens in April for a cost of $22,733.03.

New comment by o10449366 in "Email could have been X.400 times better"

o10449366 — Sat, 25 Apr 2026 15:06:34 +0000

Yes, I throw away maybe 98% of the physical mail I receive. But I have to sort through it for the 2% that's maybe important and for some reason MUST be received by physical mail.

There's obviously a lot of physical waste in this day and age and it's arguably small by comparison, but the paper waste from mail spam still disgusts me.

New comment by o10449366 in "An update on recent Claude Code quality reports"

o10449366 — Thu, 23 Apr 2026 20:06:57 +0000

Yeah and that statement also speaks to their test rigor if they make a change that big without thoroughly testing the edge case they're modifying.

New comment by o10449366 in "An update on recent Claude Code quality reports"

o10449366 — Thu, 23 Apr 2026 19:47:52 +0000

Resuming from sessions are still broken since Feb (I had to get claude to write a hook to fix that itself), the monitoring tool doesn't work and blocks usage of what does (simple sleep - except it doesn't even block correctly so you just sidestep in more ridiculous ways), and yet there seems to be more annoying activity proxies/spinner wheels (staring into middle distance)... Like I don't know how in a span of a few months you lose such focus on your product goals. Has Anthropic reached that point in their lifecycle already where their product team is no longer staffed by engineers and they have more and more non-technical MBAs joining trying to ride the hype train?

New comment by o10449366 in "ChatGPT Images 2.0"

o10449366 — Wed, 22 Apr 2026 06:44:06 +0000

When you program, do you consider using your prior knowledge of programming cheating?

New comment by o10449366 in "Claude Token Counter, now with model comparisons"

o10449366 — Mon, 20 Apr 2026 18:16:54 +0000

So it sounds like you were using it on auto mode then if it went ahead and fixed the vulnerabilities without additional turns? If so, that isn't really a single prompt.

New comment by o10449366 in "Qwen3.6-Max-Preview: Smarter, Sharper, Still Evolving"

o10449366 — Mon, 20 Apr 2026 18:07:29 +0000

I have the M3 Max MBP with 128 GB of memory and the 40 core GPU. What's the best local model I can run today for coding?

New comment by o10449366 in "Claude Token Counter, now with model comparisons"

o10449366 — Mon, 20 Apr 2026 13:08:06 +0000

What was your single prompt? That seems highly unlikely.

New comment by o10449366 in "DaVinci Resolve – Photo"

o10449366 — Tue, 14 Apr 2026 09:43:40 +0000

Softbox lighting and it looks off because obviously no one lights their work desk like they would for a professional photo shoot.

New comment by o10449366 in "Backblaze has stopped backing up your data"

o10449366 — Tue, 14 Apr 2026 09:13:23 +0000

I've recently been looking for online backup providers and Backblaze came highly recommended to me - but I think after reading this article I'll look elsewhere because this kind of behavior seems like the first step on the path of enshittification.

New comment by o10449366 in "US and Iran agree to provisional ceasefire"

o10449366 — Wed, 08 Apr 2026 08:03:34 +0000

Is it terrorism? radicalization seems like a pretty natural human response when your family/home/community gets indiscriminately obliterated by missiles from the sky.

New comment by o10449366 in "US and Iran agree to provisional ceasefire"

o10449366 — Wed, 08 Apr 2026 08:01:06 +0000

gee, i wonder who helped put those religious fanatics in power and have helped them retain power by raining down death from the sky

New comment by o10449366 in "Amazon holds engineering meeting following AI-related outages"

o10449366 — Tue, 10 Mar 2026 06:09:51 +0000

Paywalled

New comment by o10449366 in "Elevated Errors in Claude.ai"

o10449366 — Tue, 03 Mar 2026 08:34:52 +0000

No wonder. It's performance overall was noticeably, like it had regressed to coding models from 1.5 years ago. I've try not to use claude during peak US hours because it tends to struggle more then with reasoning and correctness it seems than off hours.

New comment by o10449366 in "Show HN: Timber – Ollama for classical ML models, 336x faster than Python"

o10449366 — Mon, 02 Mar 2026 05:28:35 +0000

Can you tell us more about the motivation for this project? I'm very curious if it was driven by a specific use case.

I know there are specialized trading firms that have implemented projects like this, but most industry workflows I know of still involve data pipelines with scientists doing intermediate data transformations before they feed them into these models. Even the c-backed libraries like numpy/pandas still explicitly depend on the cpython API and can't be compiled away, and this data feed step tends to be the bottleneck in my experience.

That isn't to say this isn't a worthy project - I've explored similar initiatives myself - but my conclusion was that unless your data source is pre-configured to feed directly into your specific model without any intermediate transformation steps, optimizing the inference time has marginal benefit in the overall pipeline. I lament this as an engineer that loves making things go fast but has to work with scientists that love the convenience of jupyter notebooks and the APIs of numpy/pandas.

New comment by o10449366 in "Cameras and Lenses (2020)"

o10449366 — Fri, 02 Jan 2026 01:12:03 +0000

Comments on AI, on an article which has nothing to do with it, are just as uninspired as AI writing.

New comment by o10449366 in "Growing up in “404 Not Found”: China's nuclear city in the Gobi Desert"

o10449366 — Sun, 28 Dec 2025 18:28:26 +0000

I mean, you're making assumptions about the author's intent going one way, but not the other. What if the polite tone is what they intended? And how do you know they didn't review the output for phrasing and fabrications?

The author acknowledged they used AI to translate. Is the translation they decided to publish among the given tools they had available to them not by definition the most authentic and intentional piece that exists?

All of this aside, how do you think tools like Google Translate even work? Language isn't a lookup table with a 1:1 mapping. Even these other translation tools that are being suggested still incorporate AI. Should the author manually look up words in dictionaries and translate word by word, when dictionaries themselves are notoriously politicized and policed, too?