Hacker News: eshack94

New comment by eshack94 in "Drawgent: Coding agent on a live Excalidraw canvas"

eshack94 — Sat, 26 Sep 2026 23:37:13 +0000

Oddly, it seems like it hasn't been touched in 6 months (and last release 7 months ago). I wonder if it's been abandoned, or simply deprioritized in favor of other work.

New comment by eshack94 in "Rate limits on GitLab.com are changing"

eshack94 — Thu, 17 Sep 2026 22:11:20 +0000

I digress, but GitHub's GraphQL API has been neglected for years. Or at the minimum, they have not maintained feature parity with their REST API, so there are a good number of cases where you simply cannot do what you need to do without using their REST API.

New comment by eshack94 in "iOS 27, iPadOS 27, and macOS 27"

eshack94 — Tue, 15 Sep 2026 00:15:04 +0000

Would you say that it's ready for prime-time on a developer machine?

New comment by eshack94 in "iOS 27, iPadOS 27, and macOS 27"

eshack94 — Tue, 15 Sep 2026 00:14:18 +0000

Should developers upgrade yet, or wait?

New comment by eshack94 in "Thanks to Siri Recaps, your Apple Watch is always listening"

eshack94 — Thu, 10 Sep 2026 15:10:57 +0000

Can this be disabled?

New comment by eshack94 in "Claude Fable 5.1 and Claude Mythos 5.1"

eshack94 — Tue, 01 Sep 2026 18:10:00 +0000

Asking the real questions. I've been wondering what the holdup on that is.

Does anyone reading this have additional knowledge or insight on this?

New comment by eshack94 in "DeepSeek V4 Pro 0813"

eshack94 — Wed, 12 Aug 2026 17:40:45 +0000

It appears that the only available endpoint (as of this writing) requires enabling "Allow paid endpoints that train on request data" in the OpenRouter privacy settings. I hope additional paid providers will become available that don't require training on data.

New comment by eshack94 in "AI is removing the middle class of software engineering?"

eshack94 — Wed, 12 Aug 2026 16:12:15 +0000

This blog post illustrates the importance of NEVER outsourcing your critical thinking or outsourcing decision-making to an LLM. And to never take shortcuts with learning. Learning is hard, but learning things properly allows you to understand what is happening and allows you to ask the right questions about whether the changes an agent wants to make are the changes that will best serve the goals of the project (without creating an unwieldy level of tech debt in the future).

Personally speaking (and I'd love to hear others' takes on this): when using an LLM for work-related and development tasks, I never use the "full-auto" mode, and I never manually approve of something that I don't understand. When I don't understand something an agent wants to do, I go on a side-quest to learn more about said thing and to educate myself first. This takes extra time, but I feel that it's the right thing to do, so I can at least approve/deny/redirect from a more informed position, rather than flying blind and hoping for the best.

In addition to what the author discusses, I think skill-atrophy, stagnation due to complacency (i.e.: "why grow and learn if an agent can do it" mindset), and cognitive laziness are additional risks that come with overrelying on LLMs. Humans were meant to think. LLMs are a tool.

New comment by eshack94 in "US Military asks troops for 'creative and unconventional' ideas to punish Iran"

eshack94 — Tue, 04 Aug 2026 15:22:31 +0000

"chocolate product", these days, or so it seems.

New comment by eshack94 in "Handbook.md shows that long policy documents do not reliably govern agents"

eshack94 — Wed, 29 Jul 2026 14:38:04 +0000

I've noticed this trend of the sampler knobs being removed. Can you explain why this might be the case?

New comment by eshack94 in "Claude Opus 4.8"

eshack94 — Thu, 28 May 2026 20:49:25 +0000

That's exactly right.

New comment by eshack94 in "Claude Opus 4.8"

eshack94 — Thu, 28 May 2026 20:47:59 +0000

The Claude Pro subscription is basically useless at this point, in terms of usage limits with respect to the settings required to achieve actual useful output.

New comment by eshack94 in "DeepSeek v4"

eshack94 — Fri, 24 Apr 2026 18:29:28 +0000

Agreed, they also have great documentation. There's something to be said for documentation that is so concise, well laid out, and immediately actionable for those looking to get started quickly.

New comment by eshack94 in "Incident with multple GitHub services"

eshack94 — Fri, 24 Apr 2026 04:51:37 +0000

At this point, I feel like there should be a HN post whenever there ISN'T an issue with some GitHub service. Otherwise, it's business as usual...

New comment by eshack94 in "Reallocating $100/Month Claude Code Spend to Zed and OpenRouter"

eshack94 — Wed, 22 Apr 2026 06:21:17 +0000

I appreciate your guidance here. Thank you very much. I will start doing this.

New comment by eshack94 in "Changes to GitHub Copilot individual plans"

eshack94 — Wed, 22 Apr 2026 02:48:07 +0000

I'm in the same boat as you. Wish I had known this before my subscription renewed. There's no longer any value in paying them for this service when I can cut them out of the equation and pay the model providers directly.

New comment by eshack94 in "Reallocating $100/Month Claude Code Spend to Zed and OpenRouter"

eshack94 — Fri, 10 Apr 2026 01:35:17 +0000

I've been thinking of doing this — using one of the "pretty good but not Opus 4.6-good, YET very cheap" models for the implementation part of more basic code features, AFTER first using Opus 4.6 high for the planning stage.

Do you think this would be a decent approach?

Also, which client would I use for this? OpenCode? I don't think Claude Code supports using other models. Thoughts?

New comment by eshack94 in "Blood test boosts Alzheimer's diagnosis accuracy to 94.5%, clinical study shows"

eshack94 — Tue, 24 Feb 2026 07:11:17 +0000

Not saying anything about the article at-hand, but assuming we were able to detect it with such certainty, I think it would greatly increase the funding, rigor, and breadth or research devoted to finding a cure or treatment that actually worked.

New comment by eshack94 in "Discord will require a face scan or ID for full access next month"

eshack94 — Mon, 09 Feb 2026 19:49:35 +0000

Is this the final straw that kills their platform?

New comment by eshack94 in "iPhone Pocket"

eshack94 — Wed, 12 Nov 2025 06:00:01 +0000

Is this a joke or are they serious with this?