Hacker News: awsanswers

New comment by awsanswers in "Bird brains (2023)"

awsanswers — Mon, 30 Mar 2026 15:46:43 +0000

If you're in tune with animals and spend time around a parrot, it's obvious there is a lot going on in their minds. They have incredible memories and their own understanding of their world. It looks simple to us but they are not simple creatures. That being said, I don't know how a bird lover can keep a bird in a cage.

New comment by awsanswers in "A few random notes from Claude coding quite a bit last few weeks"

awsanswers — Wed, 28 Jan 2026 19:26:59 +0000

It's predictable so you run defense around it with prompting, validation and model tuning. It generates volumes of working code in seconds from natural language prompts so it's extremely business efficient. We're talking about tools that generate correct code to 95% of a solution, the follow up human and automated test review, and second coding pass to fix the 5% are a non issue.

New comment by awsanswers in "Show HN: eBPF Based Unlimited Hotspot for Android"

awsanswers — Fri, 14 Nov 2025 20:23:21 +0000

I had ChatGPT explain why this is works as a unlimited hotpot. Very cool: "It works because carriers detect tethering partly by looking at TTL values. Android subtracts 1 from TTL when hotspot/tethering packets are forwarded, so the carrier sees a different TTL and knows the traffic came from a tethered device. Your eBPF program increments the TTL back by +1, hiding the fact that the packet was forwarded through your phone. So to the carrier, the traffic looks like it originated directly from the phone, not from a tethered device. That defeats one of the carrier’s tethering-detection methods."

New comment by awsanswers in "Would You Use ChatGPT to Cheat at Hobbies?"

awsanswers — Fri, 07 Nov 2025 02:05:03 +0000

There is a vague current popular idea that consulting LLM output as part of decision making is somewhat morally gray. This notion is not going to age well (or even ring true) in the near term. LLMs are simply a new way to store and use information and have their own warts, which can be said about all methods of information transmission.

New comment by awsanswers in "SWE-Grep and SWE-Grep-Mini: RL for Fast Multi-Turn Context Retrieval"

awsanswers — Thu, 16 Oct 2025 19:59:40 +0000

LLM product managers: Show me what's in the context convenient to where I am prompting. Likely the user knowing and editing the precise context between requests will be a user task for a long time

New comment by awsanswers in "Playball – Watch MLB games from a terminal"

awsanswers — Fri, 03 Oct 2025 14:04:22 +0000

I love this, it feels like something that should have always existed. great job

New comment by awsanswers in "Apple and Amazon will miss AI like Intel missed mobile"

awsanswers — Tue, 19 Aug 2025 13:48:38 +0000

I don't think the author understands Amazon's AI product offering or what gen AI is doing internally at Amazon.

New comment by awsanswers in "Show HN: asyncmcp – Run MCP over async transport via AWS SNS+SQS"

awsanswers — Thu, 10 Jul 2025 22:08:44 +0000

Strongly agree with this approach. Real world task specific LLM query workloads tend to be long lived workflows. They should be brokered and handled rather than wait on.

New comment by awsanswers in "Why LLMs Can't Write Q/Kdb+: Writing Code Right-to-Left"

awsanswers — Thu, 10 Jul 2025 01:13:07 +0000

I fully discount the right to left thing.

There is not enough q/kdb full source code "out there" that would have made it into the LLM training data. It tends to be used in secretive environments and can be very site specific in convention. I bet a purpose built small fine tune with real + synthetic data would be enough to get something generating better Q code.

New comment by awsanswers in "People with Diabetes Are Cured in Small Trial of New Stem Cell-Based Drug"

awsanswers — Wed, 25 Jun 2025 03:18:34 +0000

There is a tradeoff, they have to take immunosuppressive drugs for the rest of their lives.

New comment by awsanswers in "Ask HN: Could we possibly be the last generation of programmers?"

awsanswers — Sun, 27 Apr 2025 16:15:16 +0000

No. The human effort will be at a higher level of the implementation. Like how there are only very specific use cases for hand writing assembly today.

New comment by awsanswers in "Tilt: dev environment as code"

awsanswers — Sun, 27 Apr 2025 03:25:37 +0000

I hadn't heard of Tilt until this year. I inherited an environment with it integrated. It's a great reliable tool

New comment by awsanswers in "AGI Is Still 30 Years Away – Ege Erdil and Tamay Besiroglu"

awsanswers — Mon, 21 Apr 2025 00:18:18 +0000

totally agree

New comment by awsanswers in "xlskubectl – a spreadsheet to control your Kubernetes cluster"

awsanswers — Thu, 13 Mar 2025 02:31:11 +0000

This is useful and necessary software. Keep going. This can be a wonderful demystifyer for some and a useful tool for others.

New comment by awsanswers in "When eBPF pt_regs reads return garbage on the latest Linux kernels, blame Fred"

awsanswers — Sat, 01 Mar 2025 03:38:26 +0000

This is interesting. Operating on the edge of user space

New comment by awsanswers in "Amazon's AI crawler is making my Git server unstable"

awsanswers — Sat, 18 Jan 2025 19:01:43 +0000

Unacceptable, sorry this is happening. Do you know about fail2ban? You can have it automatically filter IPs that violate certain rules. One rule could be matching on the bot trying certain URLs. You might be able to get some kind of honeypot going with that idea. Good luck

New comment by awsanswers in "Ask HN: What's going to happen when they fail to deliver AGI in 5 years time?"

awsanswers — Thu, 16 Jan 2025 14:04:55 +0000

If we were somehow stuck with our current models, there would still be about 10 years of finding more and more useful ways of using them. If we don't have AGI in 5 years we'll have something quite close to it.

New comment by awsanswers in "AWS randomly assigns AZ names differently across accounts"

awsanswers — Wed, 27 Nov 2024 19:50:02 +0000

To prevent the effect of people picking the first zone in the list to launch resources into

New comment by awsanswers in "Meta loses ground to Bluesky as users abandon Elon Musk's X"

awsanswers — Sun, 24 Nov 2024 06:31:36 +0000

Bluesky has zero popular cultural adoption and users are already weirded out by extreme left influence on the discourse. I set a calendar to check this post in 18 months, now we wait

New comment by awsanswers in "S3 Express Append has issues"

awsanswers — Sun, 24 Nov 2024 01:29:17 +0000

I happen to know the content on this blog, the tone of this article and quality of content is not usually like this. What happened?