HackerNews
Ask HN: Are AI credits too locked to individual applications?
The problem: I already had AI credits, but those credits were locked to one application. context : I was using both an agentic IDE and a Hostinger deployment agent. One day, I ran out of credits on the deployment agent. To keep using it, I either had to wait for credits to reset or upgrade to a higher subscription or buy tokens. At the same time, I already had a subscription for the IDE, but I could not use those credits on Hostinger. simply despite having credits, we cannot use them. Is this ac...
HackerNews
Show HN: 4bit bridge between AI and humans
Article URL: https://github.com/YOalphabet/YOalphabet
Comments URL: https://news.ycombinator.com/item?id=49356777
Points: 3
# Comments: 1
HackerNews
AI mines 500 years of Spanish colonial records to find hidden wrecks, lost cargo
Article URL: https://www.tomshardware.com/tech-industry/artificial-intelligence/ai-company-hiring-a-literal-pirate-to-salvage-sunken-treasure-found-by-artificial-intelligence-pays-up-to-usd500k-a-year-mining-80-million-pages-of-spanish-colonial-records-to-find-undiscovered-wrecks-and-lost-cargo
Comments URL: https://news.ycombinator.com/item?id=49356812
Points: 3
# Comments: 0
HackerNews
Looking for an ArXiv Endorser – AI / Computer Science
Article URL: https://github.com/paibyun9/EGA-V9
Comments URL: https://news.ycombinator.com/item?id=49357141
Points: 1
# Comments: 2
HackerNews
AI Stock Research Assistant · Streamlit
Article URL: https://ai-stock-research-kiaan.streamlit.app
Comments URL: https://news.ycombinator.com/item?id=49357163
Points: 1
# Comments: 1
HackerNews
Get feedback on your AI slop. no accounts
Article URL: https://slopornot.simplicated.dev
Comments URL: https://news.ycombinator.com/item?id=49357213
Points: 1
# Comments: 0
HackerNews
Designing AI with character: what we learned building Berd
Article URL: https://block.xyz/inside/designing-ai-with-character-what-we-learned-building-berd
Comments URL: https://news.ycombinator.com/item?id=49357223
Points: 1
# Comments: 0
HackerNews
Does AI stop children from learning?
Article URL: https://www.economist.com/graphic-detail/2026/08/18/does-ai-stop-children-from-learning
Comments URL: https://news.ycombinator.com/item?id=49357530
Points: 4
# Comments: 0
HackerNews
200B Tokens Later: A Month of Letting AI Agents Decompile MW2
Article URL: https://momo5502.com/posts/2026-08-17-mw2-decompilation/
Comments URL: https://news.ycombinator.com/item?id=49357584
Points: 2
# Comments: 0
HackerNews
Excited and exhausted: life as a tech writer in the AI age
Article URL: https://elizabethtai.com/2026/08/19/life-as-a-techwriter-in-the-ai-age/
Comments URL: https://news.ycombinator.com/item?id=49357621
Points: 1
# Comments: 0
HackerNews
Building Shared Memory for AI Agents in Notion
Article URL: https://www.notion.com/blog/building-shared-memory-for-ai-agents-in-notion
Comments URL: https://news.ycombinator.com/item?id=49357879
Points: 2
# Comments: 0
HackerNews
AI's recursive self-improvement might not come so quickly after all
Article URL: https://www.technologyreview.com/2026/08/18/1142188/ai-recursive-self-improvement/
Comments URL: https://news.ycombinator.com/item?id=49357929
Points: 1
# Comments: 0
HackerNews
Young adults in the US are increasingly wary of AI, concerned it will take jobs
Article URL: https://www.pewresearch.org/short-reads/2026/08/18/young-adults-in-the-us-are-increasingly-wary-of-ai-concerned-it-will-take-jobs/
Comments URL: https://news.ycombinator.com/item?id=49357941
Points: 3
# Comments: 0
HackerNews
AI is accelerating elder fraud. Their kids are reckoning with the fallout
Article URL: https://www.usatoday.com/story/life/health-wellness/2026/08/18/elder-fraud-ai-sandwich-generation-caregivers/90852035007/
Comments URL: https://news.ycombinator.com/item?id=49357950
Points: 4
# Comments: 0
HackerNews
Vetted AI code is hard to justify
Article URL: https://amoffat.github.io/blog/vetting-burnout.html
Comments URL: https://news.ycombinator.com/item?id=49358041
Points: 1
# Comments: 2
HackerNews
Trump crypto firm backs venture offering AI from restricted Chinese companies
Article URL: https://www.reuters.com/world/china/trump-crypto-firm-backs-venture-offering-ai-restricted-chinese-companies-2026-08-17/
Comments URL: https://news.ycombinator.com/item?id=49358077
Points: 1
# Comments: 0
HackerNews
AI-generated candidate proof of a causal guarantee for RACE attention [pdf]
Article URL: https://drive.google.com/file/d/11Jh_ITQWQbM40REfNayPbS98lyk0EUTG/view?usp=drive_link
Comments URL: https://news.ycombinator.com/item?id=49358146
Points: 1
# Comments: 0
HackerNews
Show HN: Open-source extension to transfer AI chats without losing context
Article URL: https://github.com/VC067/MoveChat
Comments URL: https://news.ycombinator.com/item?id=49358171
Points: 1
# Comments: 0
HackerNews
Show HN: Superprez.io – Sharing and Collaboration for AI-Generated Decks
Hi HN,
I've been working on Superprez.io because of something that started bothering me more and more with AI-generated presentations. Any AI like Claude, Cursor and ChatGPT can now generate surprisingly good decks — not just visually, but with animations, interactive elements, embedded products, maps, live polling, etc. But a lot of these presentations are ultimately treated like traditional presentations: export them to PDF or PPT and send them around.
And that's where a lot of what makes them...
HackerNews
AI Marketing Stash: a directory for discovering AI marketing tools
Article URL: https://www.aimarketingstash.com
Comments URL: https://news.ycombinator.com/item?id=49358251
Points: 1
# Comments: 0
🌍 Dev.to
Clop's Windchill Web Shell: From Credential Decryption to Design Data Theft Inside the App
Clop's Windchill Web Shell: From Credential Decryption to Design Data Theft Inside the App
1. Basic Information
Article Title : Clop Returns with Custom Implant in Mass-Extortion Campaign
Publisher : ReliaQuest Threat Research Team
Publication Date : 2026-08-18
Severity : Critical
Original Source : ReliaQuest
Related Sources : BleepingComputer , Ransom-ISAC
Related Malware & Threat Groups : Clop / Cl0p, Windchill-specific JSP Web Shell
...
🌍 Dev.to
Forminator Forms (CVE-2026-15748): Unauthenticated RCE via Forged Upload Settings in Select Fields
Forminator Forms (CVE-2026-15748): Unauthenticated RCE via Forged Upload Settings in Select Fields
1. Basic Information
Article Title : 600,000 WordPress Sites Affected by Arbitrary File Upload Vulnerability in Forminator Forms WordPress Plugin
Publisher : Wordfence Intelligence
Publication Date : 2026-08-17
Severity : High
Original Source : Wordfence
Related Sources : SecurityWeek
Related Malware / Attack Groups : None / Unidentified
CVE &a...
🌍 Dev.to
The Hottest AI Framework Right Now Has a Fatal Flaw Nobody Mentions
I spend a lot of time in the AI space -- reading papers, building things, talking to engineers who are actually shipping. And there is a gap between what the demos show and what production systems actually look like that nobody is being fully honest about.
So here is my honest take on where things actually are.
The Problem With How We Talk About AI Agents
Everyone is calling everything an "agent" right now. A function that calls a tool? Agent. A chatbot with memory? Agent. ...
🌍 Dev.to
My QUIC transport had never once been executed. Here's what happened when I ran it.
I've written before about SMESH, a coordination protocol modelled on mycorrhizal networks — the fungal web that lets trees in a forest warn each other about drought and disease with nothing in charge of the network. Signals diffuse, decay on their own, and get reinforced when independently confirmed. Consensus emerges instead of being orchestrated.
That was the idea. This post is about the part where I found out whether it worked.
The transport that had never run
SMESH has had...
🌍 Dev.to
UFW and WireGuard: the tunnel is up and nothing goes through
The tunnel comes up. wg show prints a recent handshake. The client has its address inside the tunnel. And not a single byte reaches the internet.
Almost every guide answers this with "open UDP 51820 in the firewall". You already did that — it is why the handshake works at all. The problem is somewhere else, and UFW makes the distinction easy to miss:
Entering a machine and traversing it are two different permissions.
ufw allow 51820/udp lets packets arrive at the server. Your cl...
🌍 Dev.to
A 2-Token Prompt and a 39,966-Token Bill: Measuring What My Agent Actually Costs
There is a small cluster of posts going around right now about auditing your LLM invoice, and about how cost calculators get the numbers wrong. I went to check mine and hit a problem before I got to the arithmetic: my pipeline doesn't produce an invoice, and the plumbing I built two months ago is the reason why.
This project has a script, git_commit.py , that turns a staged git diff into a Conventional Commit message. It shells out to the Claude CLI. There is no ANTHROPIC_API_KEY anywhere ...

🌍 Dev.to
Tokens per Second Benchmarks Explained: What You're Actually Measuring
What tok/s really measures, how concurrency changes it, and why a single-user benchmark is not the whole story for local LLM performance.
A Few Moments Later… How Fast Is "Fast"?
Every interface in the world of local AI eventually shows you that dreaded spinner, and on the wrong setup it sits there long enough that your brain supplies the meme: "A few moments later…" That pause is a number wearing a disguise. Somewhere inside your machine, the model is grinding out tokens —...
🌍 Dev.to
🛡️ Arquitectura de Defensa para Agentes de IA: Cómo asegurar tus LLMs contra Prompt Injection, Tool-Poisoning y Fugitividad.
🛡️ Arquitectura de Defensa para Agentes de IA: Cómo asegurar tus LLMs contra Prompt Injection, Tool-Poisoning y Fugitividad.
El ecosistema actual de agentes autónomos y servidores MCP (Model Context Protocol) es brillante, pero operativamente es una pesadilla de seguridad. Estamos construyendo sistemas que ejecutan código, acceden a bases de datos y toman decisiones críticas basándose en salidas de texto que son intrínsecamente manipulables.
Si estás desplegando agentes en producción conf...
🌍 Dev.to
Marketplace Call Summarization API: Multiple Documents, Async Jobs, Verified CRM Exports
TL;DR
For marketplace sales calls, use an async job when several documents must become one reviewed set of CRM actions; use an inline request only when one short document can finish inside the caller's latency budget. Preserve one result per input, expose partial progress, and export only records that carry their source ID, outcome, and schema version.
Start with this decision table:
Pick
Use it when
Quality and latency consequence
Operational burden
Inline reque...