Hacker News: davesque

New comment by davesque in "Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw"

davesque — Sat, 04 Apr 2026 03:38:06 +0000

I'm honestly completely in favor of this. Anthropic obviously budgets their capacity based on projected human usage patterns coming through their native app suite (Claude Cowork, Claude Code, etc.). They should not be expected to shoulder the burden of community tools like OpenClaw that are effectively designed to strategically max out usage windows on the plan. That has clearly caused issues with uptime in the past couple of months and I've gotten pretty fed up with the degraded service quality while I'm just trying to use Claude Code as it's intended to be used. I'm happy to see they're doing something about this. Seems like a totally fair move to me. I'd rather that Claude Code functions well when I'm using it according to its design.

New comment by davesque in "Qwen3.6-Plus: Towards real world agents"

davesque — Thu, 02 Apr 2026 22:24:38 +0000

I wish these AI vendors would quit publishing comparisons with the previous generation of their competitors's models. It's just such a glaringly bad look and no one is fooled by it, even if their achievements deserve praise in their own right. The Qwen models are great and don't deserve the reputational hit that comes from dodgy marketing tactics.

New comment by davesque in "Ollama is now powered by MLX on Apple Silicon in preview"

davesque — Tue, 31 Mar 2026 20:41:33 +0000

Yeah omlx seems to me like the front runner right now for running MLX models locally in agent workflows (which depend heavily on caching).

New comment by davesque in "Claude Code users hitting usage limits 'way faster than expected'"

davesque — Tue, 31 Mar 2026 20:34:48 +0000

I'm not sure this is the issue. I asked Claude Code a simple question yesterday. No sub agents. No web fetches. Relatively small context. Outside of peak hours. Burned 8% of my Max 5x 5hr usage limit. I've never seen anything like this before, even when the cache is cold.

New comment by davesque in "Learn Claude Code by doing, not reading"

davesque — Tue, 31 Mar 2026 01:49:25 +0000

You don't. Most of the time (after the first prompt following a compaction or context clear) the context prefix is cached, and you pay something like 10% of the cost for cached tokens. But your total cost is still roughly the area under a line with positive slope. So increases quadratically with context length.

New comment by davesque in "TurboQuant: Redefining AI efficiency with extreme compression"

davesque — Thu, 26 Mar 2026 01:23:30 +0000

Yeah, the viz for polar quantization is straight up nonsensical. Okay, so some colors are converted into clocks and then into a bigger box with a pink box inside of it. Got it. Even understanding what polar coordinates are doesn't help you make sense out of it.

New comment by davesque in "TurboQuant: Redefining AI efficiency with extreme compression"

davesque — Wed, 25 Mar 2026 17:28:03 +0000

Yeah, and some parts of the article are just bizarre:

> Instead of looking at a memory vector using standard coordinates (i.e., X, Y, Z) that indicate the distance along each axis, PolarQuant converts the vector into polar coordinates using a Cartesian coordinate system. This is comparable to replacing "Go 3 blocks East, 4 blocks North" with "Go 5 blocks total at a 37-degree angle”

Why bother explaining this? Were they targeting the high school and middle school student reader base??

New comment by davesque in "Robert Mueller Has Died"

davesque — Sat, 21 Mar 2026 19:40:08 +0000

I believe technically this means I'm free to crack a bottle of champagne when Trump dies and incur no negative karma at all!

New comment by davesque in "Claude now creates interactive charts, diagrams and visualizations"

davesque — Thu, 12 Mar 2026 20:13:56 +0000

The Claude Code TUI app is pretty solid. I use it heavily and I get great results from it. But with the mobile app, Claude Code remote is basically unusable (weird disconnect bugs) and Claude Code cloud has issues as well (UI hides approval confirmations; must reconnect to see them). So yeah, I imagine what you're saying is true. There are at least some major gaps in their QA process. It's ironically a pretty convincing case to keep humans in the loop. It's honestly shocking to me that those features were actually shipped in their current state. You run into the problems immediately.

New comment by davesque in "Our Agreement with the Department of War"

davesque — Sun, 01 Mar 2026 00:38:12 +0000

i.e. Combing through public forums on the internet looking for evidence of thought crime, however, is fair game. The Trump admin will undoubtedly use tools like this to compile a list political enemies or undesirables, which they will then use to harass people or selectively restrict individual rights. They're already doing this and this is just going to make it easier for them.

New comment by davesque in "We Will Not Be Divided"

davesque — Sat, 28 Feb 2026 21:13:25 +0000

I don't think it will feel even remotely tolerable in the US. I've been heavily critical of Trump on a regular basis on the public internet ever since he showed up 10 years ago. I doubt a government surveillance AI would miss this. Of course, there are probably millions of people like me, but given the behavior of the government recently, I really have to wonder what they might do to people like me once we've been put on a list.

New comment by davesque in "Will vibe coding end like the maker movement?"

davesque — Thu, 26 Feb 2026 22:03:58 +0000

I don't understand this. I use agentic coding to do things more quickly. And it's not just toys. I end up with software that both works and is useful. Assuming AI models powerful enough to drive that process continue to be available, why would I stop doing it?

New comment by davesque in "Qwen3.5: Towards Native Multimodal Agents"

davesque — Wed, 25 Feb 2026 22:08:20 +0000

Did it do that because it's better at logic or because internet commentary on this embarrassing question is now part of the training set?

New comment by davesque in "Facebook is cooked"

davesque — Fri, 20 Feb 2026 18:42:30 +0000

It's a complete mystery to me how Facebook operates. Like, they need money to keep the lights on, right? Where is the money coming from if no humans are using the platform?

New comment by davesque in "Trump revokes landmark ruling that greenhouse gases endanger public health"

davesque — Fri, 13 Feb 2026 04:00:26 +0000

It's not hard to imagine that he did this on a whim; that's his nature. He does it all the time, including with important economic policy, such as tariffs. Impulsively making important decisions without a sound reasoning process is dimwitted behavior. Isn't it obvious that Trump is an impulsive decision maker?

New comment by davesque in "Trump revokes landmark ruling that greenhouse gases endanger public health"

davesque — Fri, 13 Feb 2026 01:22:29 +0000

I continue to be confused as to how one dimwit can make so many consequential decisions for all of us. And we just have to sit here like idiots and can't seem to do anything about it.

New comment by davesque in "Flock CEO calls Deflock a “terrorist organization” (2025) [video]"

davesque — Thu, 05 Feb 2026 23:17:13 +0000

It hasn't been though. These clowns are just using the term disingenuously.

New comment by davesque in "Flock CEO calls Deflock a “terrorist organization” (2025) [video]"

davesque — Thu, 05 Feb 2026 23:13:15 +0000

I think the clerk who wouldn't accept my return at Home Depot is a terrorist. Also my cat.

New comment by davesque in "We Used To Build Things. What Happened?"

davesque — Thu, 05 Feb 2026 03:02:16 +0000

The wealthy also stopped paying taxes so...what does this rich guy want exactly?

New comment by davesque in "Nvidia Stock Crash Prediction"

davesque — Wed, 21 Jan 2026 02:45:41 +0000

> Nvidia has been around long enough and has enough market penetration in datacenters and gaming that I don't think it's going to go bust, and I figure that it will eventually appreciate again just due to inflation.

Shouldn't the same argument also apply to Intel?