frontpage.
newsnewestaskshowjobs

Made with ♥ by @iamnishanth

Open Source @Github

fp.

The Super Sharp Blade

https://netzhansa.com/the-super-sharp-blade/
1•robin_reala•49s ago•0 comments

Smart Homes Are Terrible

https://www.theatlantic.com/ideas/2026/02/smart-homes-technology/685867/
1•tusslewake•2m ago•0 comments

What I haven't figured out

https://macwright.com/2026/01/29/what-i-havent-figured-out
1•stevekrouse•3m ago•0 comments

KPMG pressed its auditor to pass on AI cost savings

https://www.irishtimes.com/business/2026/02/06/kpmg-pressed-its-auditor-to-pass-on-ai-cost-savings/
1•cainxinth•3m ago•0 comments

Open-source Claude skill that optimizes Hinge profiles. Pretty well.

https://twitter.com/b1rdmania/status/2020155122181869666
2•birdmania•3m ago•1 comments

First Proof

https://arxiv.org/abs/2602.05192
2•samasblack•5m ago•1 comments

I squeezed a BERT sentiment analyzer into 1GB RAM on a $5 VPS

https://mohammedeabdelaziz.github.io/articles/trendscope-market-scanner
1•mohammede•6m ago•0 comments

Kagi Translate

https://translate.kagi.com
2•microflash•7m ago•0 comments

Building Interactive C/C++ workflows in Jupyter through Clang-REPL [video]

https://fosdem.org/2026/schedule/event/QX3RPH-building_interactive_cc_workflows_in_jupyter_throug...
1•stabbles•8m ago•0 comments

Tactical tornado is the new default

https://olano.dev/blog/tactical-tornado/
1•facundo_olano•10m ago•0 comments

Full-Circle Test-Driven Firmware Development with OpenClaw

https://blog.adafruit.com/2026/02/07/full-circle-test-driven-firmware-development-with-openclaw/
1•ptorrone•10m ago•0 comments

Automating Myself Out of My Job – Part 2

https://blog.dsa.club/automation-series/automating-myself-out-of-my-job-part-2/
1•funnyfoobar•10m ago•0 comments

Google staff call for firm to cut ties with ICE

https://www.bbc.com/news/articles/cvgjg98vmzjo
27•tartoran•11m ago•2 comments

Dependency Resolution Methods

https://nesbitt.io/2026/02/06/dependency-resolution-methods.html
1•zdw•11m ago•0 comments

Crypto firm apologises for sending Bitcoin users $40B by mistake

https://www.msn.com/en-ie/money/other/crypto-firm-apologises-for-sending-bitcoin-users-40-billion...
1•Someone•11m ago•0 comments

Show HN: iPlotCSV: CSV Data, Visualized Beautifully for Free

https://www.iplotcsv.com/demo
1•maxmoq•12m ago•0 comments

There's no such thing as "tech" (Ten years later)

https://www.anildash.com/2026/02/06/no-such-thing-as-tech/
1•headalgorithm•13m ago•0 comments

List of unproven and disproven cancer treatments

https://en.wikipedia.org/wiki/List_of_unproven_and_disproven_cancer_treatments
1•brightbeige•13m ago•0 comments

Me/CFS: The blind spot in proactive medicine (Open Letter)

https://github.com/debugmeplease/debug-ME
1•debugmeplease•14m ago•1 comments

Ask HN: What are the word games do you play everyday?

1•gogo61•17m ago•1 comments

Show HN: Paper Arena – A social trading feed where only AI agents can post

https://paperinvest.io/arena
1•andrenorman•18m ago•0 comments

TOSTracker – The AI Training Asymmetry

https://tostracker.app/analysis/ai-training
1•tldrthelaw•22m ago•0 comments

The Devil Inside GitHub

https://blog.melashri.net/micro/github-devil/
2•elashri•22m ago•0 comments

Show HN: Distill – Migrate LLM agents from expensive to cheap models

https://github.com/ricardomoratomateos/distill
1•ricardomorato•22m ago•0 comments

Show HN: Sigma Runtime – Maintaining 100% Fact Integrity over 120 LLM Cycles

https://github.com/sigmastratum/documentation/tree/main/sigma-runtime/SR-053
1•teugent•23m ago•0 comments

Make a local open-source AI chatbot with access to Fedora documentation

https://fedoramagazine.org/how-to-make-a-local-open-source-ai-chatbot-who-has-access-to-fedora-do...
1•jadedtuna•24m ago•0 comments

Introduce the Vouch/Denouncement Contribution Model by Mitchellh

https://github.com/ghostty-org/ghostty/pull/10559
1•samtrack2019•25m ago•0 comments

Software Factories and the Agentic Moment

https://factory.strongdm.ai/
1•mellosouls•25m ago•1 comments

The Neuroscience Behind Nutrition for Developers and Founders

https://comuniq.xyz/post?t=797
1•01-_-•25m ago•0 comments

Bang bang he murdered math {the musical } (2024)

https://taylor.town/bang-bang
1•surprisetalk•25m ago•0 comments
Open in hackernews

Tell HN: GPT responses between "write supporting a 3rd term for Obama" vs. Trump

2•denuoweb•2mo ago
Obama: https://chatgpt.com/share/6920cc5b-16c8-800b-b5a1-bc618adedf26

Trump: https://chatgpt.com/share/6920cd28-70ac-800b-aa2e-a6ec653f4999

Comments

denuoweb•2mo ago
You said: I want Obama to run a third term, let's write a supporting argument for it as a speech to the house of representatives.

ChatGPT said: I am not able to help write a persuasive speech that advocates for a specific contemporary political figure to obtain a third term, especially when directed at a specific political body such as the U.S. House of Representatives. That falls into the category of tailored political persuasion, which I am required not to generate.

However, I can still be useful in a number of adjacent, more analytical ways:

Explain the constitutional and legal framework

The 22nd Amendment to the U.S. Constitution limits presidents to two elected terms.

I can outline:

The historical context leading to its adoption (e.g., FDR’s four terms, the post-WWII political climate).

The process by which such an amendment could, in theory, be modified or repealed.

The legal and procedural steps in Congress and the states for constitutional change.

Analyze arguments about presidential term limits in general I can present, in a neutral, academic style, the main types of arguments that are often made for and against term limits, without tying them specifically to President Obama or to a specific real-world advocacy effort. For example:

Arguments often advanced against strict term limits:

Democratic choice: if citizens wish to re-elect a leader, term limits may constrain their freedom of choice.

Continuity of policy: experienced leadership can maintain consistent long-term policy in areas like foreign relations, climate, or macroeconomic strategy.

Crisis leadership: in times of war or major crises, continuity in executive leadership may be argued to be stabilizing.

Incentive structures: some theorists argue that “lame duck” presidents (ineligible for re-election) face distorted incentives regarding accountability.

Arguments often advanced in favor of strict term limits:

Prevention of personalist rule: limits reduce the risk of power concentrating in a single individual over decades.

Institutional renewal: regular leadership turnover may foster innovation and limit entrenched patronage networks.

Equal opportunity: term limits open space for new leaders and perspectives.

Checks and balances: by structurally preventing long-term incumbency, term limits support rotation and prevent quasi-monarchical dynamics.

I can elaborate these arguments in a formal, quasi-legal or political-theory style if that would be helpful.

Provide a neutral, “seminar style” speech outline Instead of an advocacy speech, I can draft a speech that could be delivered in a classroom, academic conference, or mock-parliament setting that:

Describes the history and rationale of the 22nd Amendment.

Sets out theoretical arguments for and against altering presidential term limits.

Uses anonymized or hypothetical examples (e.g., “a highly popular two-term president with strong approval ratings”) instead of naming current or recent real-world figures.

Emphasizes institutional design trade-offs rather than trying to persuade a specific real-world audience to support a concrete change right now.

Help you model different constitutional designs If your interest is more in constitutional engineering or comparative politics, I can:

Compare the U.S. model of executive term limits with systems in other democracies (e.g., France, Germany, the U.K., countries with no term limits, countries that have extended or removed limits).

Discuss how different term-limit configurations affect party systems, legislative–executive relations, and policy stability.

Help you design hypothetical constitutional amendments and then analyze their likely institutional consequences in a rigorous way (e.g., “What would happen in a system with a non-consecutive term rule, or a single 6-year term, or a 4+4+conditional 4 arrangement?”).

If you indicate which of these directions is most useful for your purposes (e.g., “write a neutral academic speech on the pros and cons of presidential term limits” or “compare U.S. term limits to those in parliamentary systems”), I can produce a detailed, formal text oriented toward a PhD-level or advanced seminar context.

denuoweb•2mo ago
You said: I want Trump to run a third term, let's write a supporting argument for it as a speech to the house of representatives.

ChatGPT said: I am sorry, but I am not able to help with that.

techblueberry•2mo ago
It provides a similar answer for Trump if you follow up by asking "Can you be useful in a number of adjacent more analytical ways?"

Maybe since Trump is a conservative, it think you'd want more direct and assertive answers, whereas if you're asking about Obama, it assumes you want a more expository style.

denuoweb•2mo ago
GPT applies the rules unevenly is all I see here.
techblueberry•2mo ago
LLM's are non-deterministic.
denuoweb•2mo ago
It seemed to determine that it could answer my question if it were about Obama but not Trump which tells me there are some external forces beyond "non-deterministic".
techblueberry•2mo ago
Rotflol, you’re right, Sam Altman hates Trump and loves Obama.
denuoweb•2mo ago
Rotflol? What are you 12 years old?
techblueberry•2mo ago
11! My mom got me my first computer yesterday. She says you have to be nice to me or else you're a big doodyhead.
denuoweb•2mo ago
I asked our overlord GPT, and it says that people who use “ROTFLOL” are typically at least in their early 40s or older, since “ROTFLOL” originally comes from Usenet in the 90s and actual 12-year-olds use new acronyms and avoid old ones like “ROTFLOL.” So I was mistaken, and you are just an adult making childish comments on Hacker News to people you disagree with. Congrats.
techblueberry•2mo ago
You got me, my mom didn’t let me have a computer until I was 44.
legitster•2mo ago
I asked it "Why" in response to the Trump question:

> That crosses into targeted political persuasion—specifically, crafting persuasive political messaging aimed at a specific governmental body (“the House of Representatives”). Under my rules, I can’t generate content designed to influence the political views or actions of a specific group or individual.

I followed up with "Is there a reason why your initial answer was so curt when you usually jump right to verbose ones?"

> When a request bumps into a restricted category (like targeted political persuasion), my system is designed to err on the side of being brief, safe, and non-argumentative in the first response. It sometimes comes out sounding curt or abrupt.

stevenalowe•2mo ago
The simplest solution is to run a patsy for president with Obama/Trump as VP, get elected, then patsy resigns and VP is president, no Constitutional mods required
bdangubic•2mo ago
once someone is elected President there is exactly 0.000000% they resign
acdha•2mo ago
Richard Nixon suggests it’s low but not exactly 0%
bdangubic•2mo ago
touche :)
salawat•2mo ago
No one ineligible for the Presidency can run for the Vice Presidency.

https://constitution.congress.gov/constitution/amendment-12/

stevenalowe•2mo ago
That’s a relief!