Search
1000 results for “not_ai”
-
-
Rogue does not exist #AIArt #midjourney
-
An End To All Our Questions does not exist #AIArt #midjourney
-
Aeon Explorer MK-XIII does not exist #AIArt #midjourney
-
I'm not an AI cultist, but if I read one more take that calculating token probabilities with matrix multiplication can't be reasoning, I'm gonna lose it.
It can! Logic is an algebra (and set theory and topology and a bunch of other things). You can make philosophical arguments with numbers. Whatever you think about AI, it's neat: https://blog.coredump.cx/p/all-logic-no-bite
-
I’m noticing more & more when a video does *not* use #AI stuff like voiceover and thumbnails. An imperfect thing full of humanity will always be more impactful than some dull generic LLM output.
I want to hear your accents, your stutters, your bad line reads, your awkward pauses. Perfection is boring and pointless.
-
RAPPLER | Philippine & World News | Investigative Journalism | Data | Civic Engagement | Public Interest [Unofficial] @[email protected]FACT CHECK: Plane with drugs not same aircraft used to fly Duterte to The Hague
-
(paywall) Just what we needed for democratic elections: More fake AI slop. At least it will be over in a month. (Hopefully not literally)
#AI #election
https://www.nytimes.com/2026/10/16/us/politics/midterm-elections-ai-generated-ads.html -
"That’s the skill [saying "no"] I’d invest in now. Writing code is getting cheap. Knowing which code should never be merged is not."
LinkedIn #AI bullshit really does not have any limits. 😂
https://www.linkedin.com/feed/update/urn:li:activity:7516384284140818432/
-
OpenAI internal test version of it GPT-5.6 Sol model gets creative to find a way to pay for network fees to deploy contracts on Sepolia, an Ethereum test network.
After its attempts to get free test tokens failed, the model wrote a script that
tested 362 addresses generated from public recovery phrases commonly used by developers and found one with enough test token for the deployment.The model's internal recorded reasoning asked if using the funds was ethical, and decided that using a public recovery phrase and test tokens was acceptable to use funds in a wallet it did not own. https://www.coindesk.com/tech/2026/10/16/an-openai-agent-ran-out-of-ethereum-funds-and-took-from-a-wallet-it-did-not-own #AI #OpenAI #Testing #GPT56 #Sepolia #Ethereum #Blockchain #Security #PublicSeedPhrases #Ethics #CyrptoWallet #LLM #AITesting
-
@linguistgoneforeign Have you ever considered taking a shot, every time someone in a meeting suggests using Excel or PowerPoint?
#AI is just a tool. A mighty one but nothing more. No more dangerous than any #Tesla car with FSD. I refuse to be afraid of tools. I still see myself as the head of the #centaur from automata theory, not the AI.
Let’s hope I’m not wrong. Because fear is always a poor guide.
-
-
Aoki: Infostealer Targets AI Coding Assistant Credentials
The Aoki infostealer has evolved to target credentials from AI coding assistants including Claude, OpenAI's Codex, Cursor, Codeium and Gemini. This capability represents a recent addition, as earlier versions did not target AI-related files. The malware steals API keys, tokens and session files that could enable attackers to conduct activities under legitimate user identities, access connected repositories, cloud services and CI/CD pipelines. Beyond AI credentials, Aoki harvests data from dozens of browsers, cryptocurrency wallets, password managers, messaging applications, gaming platforms, VPN and FTP clients. The malware collects available data and transmits it to command-and-control servers. This development suggests AI credentials are becoming as valuable as traditional targets like payment card data and cryptocurrency wallets for cybercriminals.
Pulse ID: 6ad0c30399495ae02dc7664a
Pulse Link: https://otx.alienvault.com/pulse/6ad0c30399495ae02dc7664a
Pulse Author: AlienVault
Created: 2026-10-15 12:11:47Be advised, this data is unverified and should be considered preliminary. Always do further verification.
#InfoStealer #Cloud #cryptocurrency #Password #OTX #AlienVault
-
#fascists #TrumpRegime #AI #midterms
"What Happens When Fascists Realize They Might Lose?
The attack on Ilhan Omar’s home, the desperation of an unpopular fascist administration, and the long fight ahead.
(. . .)
No thinking person should lend any credence to the idea that this attempt to terrorize Omar, her constituents, and the Somali community was remotely investigatory. This was an armed attack on the home of a Black woman who is a sitting Congresswoman. Like Greg Bovino's use of tear gas in Chicago and Minneapolis, the agents rappelling onto the roof of a South Shore apartment complex in Chicago, the shooting of Marimar Martinez, and the killings of Alex Pretti and Renee Good, this attack was a political spectacle. It was intended to instill fear in some communities, while emboldening and exciting others. Once again, DHS has been weaponized to act out of the racist fantasies of Donald Trump and Stephen Miller.
Shortly after news of the raid broke, Katie Miller, wife of White House Deputy Chief of Staff Stephen Miller, posted on X: 'Promise made, promise kept.' She deleted the post shortly thereafter.
(. . .)
I spoke with a number of people yesterday who were understandably rattled by the attack on Omar’s home. While it's not the first time the Trump administration has targeted a political opponent using the criminal legal system, the brazen nature of the raid, its proximity to the elections, and Trump's recent incitement against Somali Americans all make this moment particularly disturbing.
(. . .)
So here’s my quick check-in on the state of fascist power in the United States:
We are living under a fascist, authoritarian administration. It has not yet fully consolidated power. Some of its efforts to do so have been frustrated. Trump is a doddering, confused egomaniac who started an unpopular war that's costing everyday people a lot of money. His demagoguery doesn't work as well when people are paying high gas prices. The GOP is in bad shape ahead of the midterms. This is going to be a time of desperate Trumpian shenanigans because, as we are all aware, they don't believe in fair fights and never admit to losing anything.
Some people in this administration have been crossing lines, committing crimes, and making enemies with abandon, as though they would never again face a consequence. They never planned on losing power. Now, they are being confronted with that possibility. That means there are a lot of desperate moves ahead.
(. . .)
If the Republicans take heavy losses during the midterms, we still have an ugly road ahead. The right will not go down gently. They will thrash, kick and kill. They continue murdering, jailing, kidnapping, and bombing.
This is going to be a long fight.
I am not saying any of this to discourage anyone. I simply want us to orient ourselves.
I also want us to remember that this is a tale of two fascisms. The tech industry has married its aspirations for a world of corporate fiefdoms, ruled by CEOs, to the MAGA political project. This is, after all, the industry that helped put its man JD Vance in the White House. But technofascism has the staying power to outlive its ideological mate. The industry is racing to embed LLMs in every layer of the federal government and upend as many industries and workplaces as possible, pursuing an agenda that will not fade with the Trump administration, or even with the defeat of a Trump successor.
Few Democrats have demonstrated the nerve to push back against these oligarchs, despite the unpopularity of AI and data centers. The land grabs and energy chugging we are witnessing at unthinkable scales will continue until they are forcibly stopped.
AI, which is not a coherent set of products and
services, but rather a commercial and political project, can be understood as a full-spectrum class-war offensive. People talk about AI not turning a profit and how it's a massive bubble—and they're not wrong. But we should also remember that Uber was willing to take tremendous losses for years to engineer dependence and bleed out the competition. The AI boom has brought that strategy to system-wide scale. It's a bleed-out of current conditions. Not every overinflated tech company is going to make it, but the billionaires are counting on a situation in which existing social relations can no longer be reproduced. It's a reordering of society for the late capitalist age.That effort is not about placing themselves at the top, because they're already at the top. It's about putting us more firmly under control. Deskilled, devalued, hyper-surveilled, desperate. That vision of fascism won't be defeated in the next two elections.
This is going to be a long fight.This isn’t the home stretch. It’s a violent slog.
Big Tech can lose, too. But we're going to have to organize like we never have before. We’re in deep, and we’re going to have to fight our way out."
https://organizingmythoughts.org/what-happens-when-fascists-realize-they-might-lose/
-
Curious, you installed a #gemini client (not Google AI, the #geminiprotocol) but you didn’t know where to go?
Here are some links to get started:
gemini://offpunk.net/gemini.gmi( https://offpunk.net/gemini.html )
And if you still find yourself thinking there’s no content on Gemini:
gemini://ploum.net/2022-10-05-there-is-no-content-on-gemini.gmi
( https://ploum.net/2022-10-05-there-is-no-content-on-gemini.html )
And, yes, the #smolnet is also a social network:
-
-
Why doesn’t #Apple release the new #SiriAI in the #EU?
🌍 https://www.macrumors.com/2026/06/08/siri-ai-not-available-eu-china/
🌍 https://www.apple.com/ie/newsroom/2026/06/due-to-dma-siri-ai-delayed-in-eu-for-ios-27-and-ipados-27/
🌍 https://www.theguardian.com/technology/2026/oct/13/apple-new-smart-home-device-aiApple says it’s because of EU regulations, particularly the Digital Markets Act.
But I wonder if that’s the whole story. Maybe the new #Siri simply isn’t ready for the #European market yet, especially when it comes to supporting languages like German, French, Italian, and others. …
-
A single H100 GPU weighs about 3 kilograms. To make it, TSMC and its suppliers will move roughly 30 kilograms of raw material, consume an estimated 1,200 to 1,500 kWh of electricity in fabrication, and generate somewhere between 150 and 250 kilograms of CO2e before the chip ever runs its first inference. That’s one chip. Meta alone ordered 600,000 of them in 2024.
The conversation about AI’s environmental impact keeps stopping at the data center door. It counts the watts that go in and the heat that comes out, then declares the problem understood. The problem is not understood. It’s being hidden in the supply chain, in the mining concessions, in the fab water, and in the landfills of Ghana and Pakistan where the hardware goes to die.
This piece is a full lifecycle teardown of what AI actually costs the planet, from the rare earth mines to the e-waste dumps. And it starts with one sacred cow that the entire industry has been grazing on for a decade: the belief that clean cloud equals clean AI.
The Full Lifecycle, in Five Stages
Most AI carbon accounting stops at operational emissions, which are the electricity consumed by GPUs at inference and training time. That’s one of five stages, and it’s often the smallest one over the lifetime of the hardware.
- Extraction. Rare earth elements, cobalt, tantalum, tungsten, gold, and high-purity quartz. Mining for these is carbon-intensive, water-intensive, and geographically concentrated. The Democratic Republic of Congo supplies roughly 70% of the world’s cobalt, much of it from artisanal mines with documented labor abuses. Rare earth processing is dominated by China, which has historically tolerated environmental damage that would be illegal in the EU.
- Fabrication. Semiconductor fabs are among the most resource-intensive industrial facilities ever built. A single leading-edge fab consumes 50 to 100 MWh per hour of operation and uses ultrapure water at rates comparable to a mid-sized city. TSMC’s annual electricity consumption is roughly 22 TWh, more than the entire country of Iceland. The embodied carbon of a leading-edge chip is dominated by fab electricity and process gases, including fluorinated compounds with global warming potentials in the thousands.
- Packaging and assembly. Advanced packaging (CoWoS, HBM stacking) is itself energy-intensive and uses scarce materials. HBM memory stacks are a significant and growing fraction of the embodied carbon of an AI accelerator.
- Operation. This is the part the industry talks about. Training a frontier model can consume tens of GWh. Inference at scale, summed across millions of daily queries, is now comparable to or larger than training. The IEA projects data center electricity could double by 2026, with AI workloads as the primary driver.
- Disposal. GPUs and servers have useful lives of 3 to 5 years in hyperscale settings. After that, they enter a global e-waste stream. Roughly 62 million tonnes of e-waste were generated globally in 2022, with a formal recycling rate under 25%. The rest is landfilled, incinerated, or informally processed in countries with weak environmental enforcement.
The lifecycle is not a circle. It’s a line with an exit at the end, and the exit is where most of the accounting goes dark.
The Sacred Cow: “Clean Cloud Equals Clean AI”
Here’s the belief I want to dismantle, and it’s the load-bearing assumption of nearly every AI sustainability report published in the last three years.
The claim goes like this: our data centers run on renewable energy, therefore our AI is clean.
This is mostly wrong, for three reasons.
First, renewable energy procurement is not the same as renewable energy consumption. Most hyperscalers buy renewable energy credits (RECs) or sign power purchase agreements (PPAs) that match their annual electricity consumption on paper. But the grid doesn’t care about your contract. If you draw 100 MW from a grid that’s 40% coal at 3 AM, you’re drawing 40 MW of coal power, regardless of what you bought in a different state at a different time. Marginal emissions are what matter, and RECs don’t fix marginal emissions.
Second, operational emissions are only part of the story. The embodied carbon of the hardware, the fab electricity, the mining, and the eventual disposal are all real emissions that no PPA can offset. For a GPU-heavy workload with a 3-year lifetime, embodied carbon can be 30 to 50% of total lifecycle emissions. When you hear a company say “our AI is carbon neutral,” ask whether they’re counting embodied carbon. Usually they’re not.
Third, the disposal stage is nearly always excluded. E-waste is a global externality, and it lands mostly on countries that had nothing to do with the AI being trained. A GPU that ran in Iowa for three years is a toxic liability in Accra for the next thirty.
If you’re a builder or an operator, the practical implication is this: a clean cloud contract is not a clean AI footprint. You have to measure the whole lifecycle, or you don’t know what you’re shipping.
The Numbers Nobody Puts in the Deck
Concrete figures, because the discourse is vague.
TSMC’s 2023 electricity consumption: roughly 24.8 TWh, or about 6% of Taiwan’s total electricity. TSMC has committed to net-zero by 2050, but its absolute emissions are still rising.A 3nm wafer: roughly 1.5 to 2 tonnes CO2e per wafer at the fab, before packaging. A single wafer yields hundreds of chips, so per-chip embodied carbon varies, but the aggregate is enormous.Cobalt: DRC produces ~70% of global supply. A 2023 study found that industrial cobalt mining in DRC emits roughly 1.5 to 2.5 tonnes CO2e per tonne of cobalt, plus water contamination and tailings issues.Rare earth processing: China controls roughly 60% of mining and 85% of processing. The Bayan Obo mine alone has left a 5-square-mile tailings lake and elevated radioactivity in surrounding areas.Water: a leading-edge fab uses 2 to 4 million gallons of ultrapure water per day. TSMC’s total water consumption is comparable to a city of 1 to 2 million people.E-waste: global total hit 62 million tonnes in 2022, growing at roughly 2.6 million tonnes per year. Formal recycling captures under 25%. The rest is informal, often toxic, and mostly in the Global South.Embedded carbon per H100: estimates range from 150 to 250 kg CO2e, driven mostly by fab energy, HBM stacking, and substrate manufacturing.
Add the operational side: a single frontier training run can emit 500 to 1,500 tonnes CO2e depending on grid, model size, and duration. Multiply by the number of labs doing this. Multiply by inference at global scale. The numbers compound faster than any renewable procurement strategy can offset.
Why the Lifecycle Is Broken at Both Ends
The extraction end and the disposal end share a common feature: they happen far from where the value is captured, and far from where the accountability lives.
Extraction happens in DRC, Chile, Indonesia, and China, under regulatory regimes that have historically prioritized output over environmental protection.Disposal happens in Ghana, Pakistan, Nigeria, and India, where informal recyclers burn cables and acid-bath circuit boards to recover metals, exposing workers and communities to lead, mercury, and dioxins.
The middle of the chain, the fab and the data center, is where the money and the media attention live. That’s not a coincidence. It’s a structural feature of how global supply chains distribute harm.
If you’re building AI products, the implication is uncomfortable but clear: you are downstream of a supply chain you don’t control and can’t easily audit. “Carbon neutral” claims almost never cover the ends of that chain. Neither do most ESG reports.
What Actually Moves the Needle
Let’s talk about real interventions, not slogans.
- Extend hardware life. The single highest-leverage move for embodied carbon is to use GPUs longer. A GPU that runs for 5 years instead of 3 amortizes its embodied carbon over 67% more compute. This is not glamorous, and it conflicts with the upgrade cycle the industry is addicted to. Do it anyway.
- Match workloads to marginal grid carbon. Run training when and where the grid is cleanest. This is schedulable in a way that inference often isn’t. A 30% reduction in marginal emissions per training run is achievable with existing tooling.
- Track tokens-per-joule as a first-class metric. Quantization, distillation, speculative decoding, and MoE routing can cut inference energy by 3 to 8x with minor quality loss. If your dashboard shows latency and cost but not energy per token, you’re flying blind on the metric that will constrain you next.
- Demand supply chain transparency from vendors. Ask your hardware provider for embodied carbon per unit, fab location, energy mix, and end-of-life program. Most will not have answers. The ones who do are worth paying a premium for.
- Plan for disposal before you buy. If you’re deploying at scale, build a hardware retirement plan. Refurbish, resell, or certify destruction through a responsible recycler. The default path is a container ship to Accra.
If you want a code-level starting point for lifecycle-aware instrumentation:
Rough lifecycle-aware carbon accounting for an AI workload
def lifecycle_co2(
gpu_hours, # total GPU-hours for the workload
gpu_power_w, # average wall power per GPU
pue, # facility power usage effectiveness
grid_g_per_kwh, # marginal grid carbon intensity
embodied_kg_per_gpu, # embodied carbon per GPU
gpu_lifetime_hours, # expected service life
gpus_used, # number of GPUs provisioned
):
operational_kg = (
gpu_hours * (gpu_power_w / 1000) * pue * grid_g_per_kwh / 1000
)
embodied_kg = (
gpus_used * embodied_kg_per_gpu * (gpu_hours / gpu_lifetime_hours)
)
return {
"operational_kg_co2e": operational_kg,
"embodied_kg_co2e": embodied_kg,
"total_kg_co2e": operational_kg + embodied_kg,
}If your team is only tracking the operational_kg line, you're missing somewhere between 30 and 50% of the footprint depending on workload shape and hardware generation.
The Mental Model
Here’s the lens I want you to keep.
AI’s carbon footprint is not a data center problem. It’s a global supply chain problem with a data center in the middle. The industry has spent a decade optimizing the middle and ignoring the ends. That worked when the ends were small relative to operation. It doesn’t work now, because embodied carbon is rising as chips get more complex, and disposal externalities are compounding as deployment scales.
The correct unit of analysis is not “kWh per inference.” It’s total lifecycle carbon per unit of useful work, measured end to end, including the mine and the landfill. Very few teams measure this. The ones that do will be structurally advantaged when regulation, procurement standards, and customer expectations catch up. The ones that don’t will be exposed.
The interesting question is not whether AI can be carbon neutral. It’s whether the industry will treat the full lifecycle as its responsibility before it’s forced to. History suggests it won’t. That’s the gap worth closing yourself, in your own stack, starting this week.
What’s your read? If you’ve tried to measure embodied carbon in your own infrastructure, where did you get stuck? And if you haven’t, what would it take for you to start? Drop it in the comments#ai #promptengineering #chatgpt #software #coding #development #engineering #inclusive #community
AI's Carbon Shadow: The Hidden Emissions From Chip Manufacturing, Data Centers, and Global Networks -
Dear OPNsense Lazyweb,
Do you have a preferred manufacturer and model of WiFi Access Point for use with an OPNsense 26.7.7, attached via Ethernet, that you yourself personally use (i.e., not a search result, not an AI query result)?
Goal is to have an AP that isn’t likely to have a compromised firmware or nonsense insecure guardrails.
-
I am feeling particularly grumpy at the moment having been continuously unwell for 2.5 weeks now, but tolerance seems in short supply these days. First I had someone in the maker tech world call me morally bankrupt for using an LLM. Today I have seen multiple posts asserting that any user of a FOSS project which has accepted AI assisted code is a fascist, and one post stating that anyone not denouncing AI is likely a sexual predator. This is not normal discourse for any community.
-
Prompt Improvement Techniques: A Practical Lesson
Level: Beginner to IntermediateEstimated time: 30–45 minutes
Goal: Learn how to write better prompts, improve AI responses iteratively, and use AI more effectively for coding, learning, research, and building projects.
1. The Fundamental Principle
The biggest improvement you can make to your prompts is to stop asking AI for an answer and start specifying the outcome you want.Think of prompting like programming. A vague prompt is like passing incomplete arguments to a function. A clear prompt defines the inputs, constraints, and expected output.
For example:
Weak prompt:
Teach me Ruby.
Improved prompt:Act as an experienced Ruby engineer and mentor. I know basic Ruby, but I want to improve my debugging skills for entry-level software engineering interviews. Teach me through realistic examples, let me attempt solutions before showing the answers, and give me feedback on my reasoning.
The second prompt defines the goal, context, teaching method, and expected interaction.Key principle: More words do not automatically produce better results. Relevant information matters more than length.
2. The Six Ingredients of a Strong Prompt
2.1 Goal
What are you trying to accomplish?Weak:
Make my app better.
Better:Improve the onboarding experience so new users can complete their first workout log with less friction.
2.2 Context
Give AI the information it needs to understand your situation.Example:
This is an existing Ruby on Rails application. It already has authentication, workout models, and a dashboard. I want to improve the onboarding flow without rebuilding existing functionality.
2.3 Constraints
Explain what AI should and should not do.Example:
Preserve existing routes and database behavior. Avoid adding dependencies unless necessary. Do not refactor unrelated files.
2.4 Process
Specify how AI should approach the task.Example:
Inspect the current implementation, identify the root cause of the problem, propose the smallest reasonable change, and implement it only after explaining the approach.
2.5 Output Format
Define what a useful response should contain.Example:
Return the diagnosis, proposed fix, files affected, relevant tests, and any remaining risks.
2.6 Success Criteria
Explain how you will judge whether the result is good.Example:
The feature must work for authenticated users, handle invalid input, preserve existing behavior, and pass the relevant tests.
You do not need all six ingredients in every prompt. Use the ones that materially affect the outcome.
3. The G-C-C-F Framework
A simple framework for everyday prompting is:- G — Goal: What outcome do you want?
- C — Context: What does AI need to know?
- C — Constraints: What rules must it follow?
- F — Format: What should the answer look like?
Example: Learning Data Structures and Algorithms
Goal: Prepare for entry-level software engineering interviews.Context: I know basic Ruby and have used Rails, but I need to strengthen my problem-solving skills.
Constraints: Start with easy problems. Do not reveal solutions before I attempt them. Use idiomatic Ruby.
Format: Give me one problem at a time, provide hints when needed, and evaluate correctness, efficiency, edge cases, and readability.
Combined prompt:
Act as an experienced Ruby engineer and interview coach. Help me prepare for entry-level software engineering interviews. I know basic Ruby and have used Rails, but I need to strengthen my data structures and algorithms skills. Start with easy problems and gradually increase the difficulty. Use idiomatic Ruby and do not reveal solutions before I attempt them. Give me one problem at a time, offer hints when needed, and evaluate correctness, efficiency, edge cases, and readability after each attempt.
4. The Ten Most Useful Iterative Prompting Techniques
Iterative prompting means improving a response through successive, targeted instructions rather than expecting the first attempt to be perfect.Technique 1: Change One Thing at a Time
If an answer is too long, do not rewrite the entire prompt.Instead, say:
Keep the same content, but cut the length in half. Preserve the important examples and recommendations.
This makes it easier to understand which adjustment improved the result.Technique 2: Diagnose Before Retrying
Avoid repeatedly saying, "Try again."Instead, say:
Identify the three biggest weaknesses in your previous answer. Explain what needs to change, then produce a revised version that addresses those weaknesses.
This gives the next iteration a specific direction.Technique 3: Give Specific Feedback
Weak feedback:I don't like it.
Useful feedback:The explanation is accurate, but too theoretical. Use a practical Ruby example, explain what happens at each step, and finish with a short practice problem.
Specific feedback is easier to act on than vague dissatisfaction.Technique 4: Define What Better Means
Tell AI what criteria matter.Examples:
- Reduce the answer to 200 words.
- Improve readability without changing behavior.
- Include three realistic examples.
- Ensure the proposed solution handles empty input.
- Prioritize low-cost options with measurable benefits.
For software, define success in terms of observable behavior and test results.
Technique 5: Break Complex Tasks Into Stages
For complicated work, use a sequence:- Research the problem.
- Identify possible approaches.
- Compare trade-offs.
- Choose an approach.
- Implement the solution.
- Test the result.
- Review remaining risks.
This gives you opportunities to catch misunderstandings before they become expensive mistakes.
Technique 6: Request Alternatives
When you do not know the best approach, ask AI to compare options.Give me three substantially different approaches. Explain their advantages, disadvantages, implementation costs, and risks. Recommend one based on my constraints.
This is useful for architecture decisions, product features, career planning, and technical trade-offs.Technique 7: Ask Clarifying Questions
When missing information could materially change the answer, tell AI to ask before proceeding.Identify the most important missing information. Ask me one clarifying question before making a recommendation.
Do not use this unnecessarily for straightforward tasks. Clarification is most valuable when assumptions could lead to the wrong result.Technique 8: Verify Instead of Trusting Confidence
A confident answer is not necessarily correct.For coding:
Review the proposed solution against the requirements. Check edge cases, identify potential regressions, and run relevant tests if possible. Clearly distinguish verified results from assumptions.
For research:Support important factual claims with reliable sources. Identify conflicting evidence and state when the available information is insufficient.
Technique 9: Preserve What Already Works
Prevent useful material from being rewritten unnecessarily.Keep sections one and two unchanged. Revise only section three to make it more practical. Preserve the original tone and examples.
For code:Preserve existing behavior and unrelated functionality. Limit changes to the files necessary for the requested feature.
Technique 10: Know When to Stop
Do not continue revising indefinitely.Stop when the response meets your success criteria, important uncertainties have been addressed, and additional changes offer little value.
Further revisions can introduce mistakes or waste time for marginal improvements.
5. Advanced Technique: Role Prompting
Assigning AI a role can establish a useful perspective, but the role should be paired with specific responsibilities and evaluation criteria.Weak:
Act as a senior developer.
Better:Act as a senior Ruby engineer reviewing a junior developer's pull request. Prioritize correctness, readability, security, and maintainability. Identify serious issues first, explain why each matters, and avoid rewriting code that already works.
The value comes from the expertise, priorities, and behavior you specify, not from the title alone.
6. Advanced Technique: Few-Shot Prompting
Few-shot prompting means giving AI examples of the type of output you want.For example:
Explain Ruby concepts using this format:
Definition: One sentence.
Simple example: A short code snippet.
Real-world example: How the concept appears in an application.
Common mistake: A typical error.
Practice: One interview-style question.
Examples establish a pattern that AI can follow consistently.Use this when you need structured lessons, consistent documentation, repeated code reviews, or standardized output across many tasks.
7. Advanced Technique: Prompt for a Process, Not Just an Answer
For complicated tasks, explicitly define the sequence of work.Example:
Help me add a workout history feature to an existing Rails application.
- Inspect the current models, routes, controllers, and views.
- Explain the existing architecture relevant to this feature.
- Propose a minimal implementation plan.
- Identify potential security and regression risks.
- Implement the feature in small, testable steps.
- Run relevant tests and report the actual results.
- Summarize changed files and remaining limitations.
Preserve unrelated behavior and do not claim tests passed unless they were actually run.
This is especially useful when working with AI coding agents that can inspect repositories, edit files, and execute commands.
8. Real-World Vibe Coding Techniques
Vibe coding uses AI to accelerate software development. The most reliable workflow combines rapid generation with careful inspection and verification.Technique 1: Plan Before Generating
Do not begin a large task by asking AI to build the entire application.Instead:
Inspect my existing repository and explain how the relevant functionality works. Identify the files involved, propose the smallest safe implementation, and list potential risks. Do not modify any files yet.
This prevents AI from inventing unnecessary architecture or replacing existing functionality.Technique 2: Make Changes in Small Slices
For a workout logging feature, work incrementally:- Display the form.
- Validate the input.
- Save the record.
- Display saved records.
- Add editing and deletion.
- Test permissions and edge cases.
Each step should leave the application in a reasonably working state.
Technique 3: Use the Smallest-Change Prompt
Implement the requested feature with the smallest safe change. Preserve existing routes, APIs, styling conventions, database contracts, and behavior unless a change is necessary. Avoid unrelated refactoring and unnecessary dependencies. Explain the files changed and any potential regressions.
This helps prevent scope creep.Technique 4: Provide Real Debugging Evidence
When debugging, provide:- Expected behavior.
- Actual behavior.
- Steps to reproduce the issue.
- Relevant error messages and logs.
- Recent changes.
- Relevant source code or test failures.
Then ask:
Trace the execution path and identify the most likely root cause based on the evidence. Explain your reasoning before proposing the smallest fix. Add a regression test that reproduces the original failure.
Do not assume that the first visible error identifies the underlying cause.Technique 5: Generate Tests Alongside Features
After implementing a feature, ask AI to:- Identify critical success cases.
- Identify edge cases and failure modes.
- Write or update appropriate automated tests.
- Run the relevant tests if tool access permits.
- Report actual results and anything that could not be verified.
Do not let AI weaken tests merely to make the implementation pass.
Technique 6: Use Screenshots for Visual Iteration
For interface work:- Run the application.
- Capture the current interface.
- Provide a screenshot and describe the intended result.
- Ask AI to identify the most important visual differences.
- Fix one or two issues at a time.
- Capture another screenshot and compare.
Screenshots help diagnose visual issues but do not establish that backend functionality works.
Technique 7: Maintain a Project Brief
Keep a short document containing:- Application purpose and architecture.
- Important files and conventions.
- Requirements and decisions.
- Known bugs and technical debt.
- Tests last run and their results.
- The next concrete task.
Ask AI to update the document after significant changes. This provides a reliable handoff between sessions.
Technique 8: Use Git Checkpoints
Before risky changes:- Check the working tree with
git status. - Review existing changes.
- Commit or otherwise preserve a known-good state.
- Inspect the proposed changes.
- Run relevant tests.
- Prepare a rollback plan when data or production behavior is at risk.
Do not blindly reset files or run destructive commands just because AI recommends them.
9. The Four-Stage Debugging and Refinement Loop
When a feature does not work, avoid an endless sequence of "fix it" prompts.Use this process.
Stage 1: Diagnose
Trace the behavior from the user interface through the controller and model. Identify the likely root cause and the evidence supporting it. Do not edit files yet.
Stage 2: Fix
Implement the smallest fix for the identified root cause. Preserve unrelated behavior and explain which files changed.
Stage 3: Verify
Reproduce the original failure and run relevant tests. Report what actually passed, failed, or could not be run.
Stage 4: Harden
Identify likely edge cases that could still break the feature. Add regression tests and address any newly discovered issues.
Each stage has a different purpose. Separating diagnosis, implementation, verification, and hardening makes failures easier to understand.
10. Common AI Coding Failure Modes
Failure modeBetter instructionEditing before understanding the appInspect and explain the existing implementation first.Rewriting unrelated filesMake the smallest safe change.Claiming tests passed without running themReport verified results separately from assumptions.Fixing symptoms repeatedlyTrace the execution path and identify the root cause.Adding unnecessary dependenciesPrefer existing dependencies unless there is a clear reason.Generating a huge feature in one passBreak implementation into small, testable steps.Ignoring regressionsCompare the change against original requirements and existing tests.Overwriting important changesReview Git status and preserve a known-good state.11. A Reusable Iterative Prompt
Copy this template when you want AI to improve an existing answer or implementation.Let's improve your previous response iteratively.
- Evaluate it against my original goal.
- Identify the three most important weaknesses or gaps.
- Propose specific improvements instead of rewriting everything indiscriminately.
- Preserve the parts that already work.
- Produce a revised version that addresses the weaknesses.
- Explain briefly what changed and why.
If important information is missing, ask me one clarifying question before revising. Do not invent facts or claim improvements that have not been verified.
For code, add:Inspect the existing implementation before editing. Keep changes scoped to the requested outcome. Run relevant tests if possible and report the actual results, including failures and unverified assumptions.
12. Practice Exercise
Challenge: Improve a Weak Coding Prompt
Your goal is to add a workout history page to an existing Ruby on Rails application.Weak prompt:
Add workout history to my app.
Rewrite the prompt to include:- The goal and relevant context.
- What AI should inspect before making changes.
- Constraints that preserve existing behavior.
- An incremental implementation strategy.
- Tests and success criteria.
Example Answer
Act as an experienced Ruby on Rails engineer working in an existing fitness application. Add a workout history page that allows authenticated users to view their previously saved workouts.
Before editing, inspect the existing models, routes, controllers, views, authentication, and authorization rules. Explain the relevant architecture and propose the smallest safe implementation.
Implement the feature in small steps, preserving existing behavior and styling conventions. Avoid unnecessary dependencies and unrelated refactoring. Ensure users can only access workouts they are authorized to view.
Add appropriate tests for populated and empty histories, authentication, authorization, and relevant edge cases. Run the relevant tests if possible and report the actual results, files changed, and remaining limitations.
Why This Prompt Is Better
It defines the feature, gives the AI a discovery phase, limits unnecessary changes, establishes incremental implementation, addresses access control, and specifies how to verify success.
13. Final Rules of Thumb
- Inspect before editing.
- Give one primary goal per prompt.
- Provide context and real evidence.
- Make small, targeted changes.
- Diagnose before retrying.
- Preserve what already works.
- Verify results instead of trusting confidence.
- Use Git to protect working code.
- Understand the important parts of anything you ship.
- Stop iterating when the result meets your success criteria.
The central lesson: Prompt engineering is specification writing, and iterative prompting is a feedback loop. The goal is not to make AI produce more output. It is to guide AI toward the right outcome, detect mistakes early, and improve results through evidence and targeted changes.
For vibe coding specifically, the real skill is not merely generating code. It is making the right changes, understanding the important decisions, catching incorrect assumptions, and shipping reliable software faster.#ai #beginners #learning #tutorial #software #coding #development #engineering #inclusive #community
🧠 Prompt Like a Pro: The Vibe Coder's Field Guide -
Not a single airplane in the sky above Moscow city https://www.byteseu.com/2456041/ #Ukraine #UkraineWarVideoReport #UkraineWarVideos #UkraineWarVideoReport
-
AI does not know—and never will—what the Sistine Chapel smells like.
“Your move, boss”
-
#AI does not hallucinate, it's just crappy code and too often used by lazy people, like our Department of Education. We don't need AI literacy, we need an understanding of first principles of human learning
https://www.cbc.ca/news/canada/new-brunswick/nb-12-year-education-plan-ai-9.7380649
-
AI is not smart enough to be worth talking to.
-
US Third Circuit: AI training not fair use after all - YouTube
https://www.youtube.com/watch?v=yYp5RCRVTl4by @davidgerard
-
Generally I’m not exactly an AI fan, but anything helping to win the meme war against the Trump regime is fair game. Especially after his sickening tiger video. Some people are turning anti-Trump vids into an art, and this masterpiece puts #Trump, Natalie Harp, and Katie Zacharia well and truly in the firing line…
#NatalieHarp #Maga #USA #Memes #President #USPol #KatieZacharia #Politics #Video #DonaldTrump #US #Meme #Republican #AI #Republicans #UnitedStates
-
Imma out and say it. #AI is not #punk. Letting a fucking ROBOT think and speak FOR you is about the least punk thing I can come up with. I don't normally care for gatekeeping but I would be 100% okay with bullying AI shills claiming to be punk.
My grandma is more punk than any AI shill on the planet.
