DEV Community • 2026-08-16 01:52

Your Browser Automation Clicks Might Be Landing 25% Off — And Nothing Will Tell You

I spent a day pointing an AI agent at a browser to publish one product across four marketplaces. Most of it worked. The parts that didn't work failed in the worst possible way: silently, with no error, no exception, and no log line. Here are the five failure modes I hit, in the order I hit them, and the probe that turned the worst one from "this site is broken" into a two-line fix. Everything be...

0 0
7m read
DEV Community • 2026-08-16 01:42

Developers you build for the future...Don't forget to be inclusive!

Developers you build for the future...Don't forget to be inclusive! I build things for blind people. I'm a braille transcriber. I work in accessibility every day. Last January, at an NFB chapter meeting, a member walked in wearing Meta Ray-Ban smart glasses. AI. Camera. Voice. Every blind person in that room wanted to know: How do we get these? So I built pifcoin.org — a charity crypto to fund...

0 0
1m read
DEV Community • 2026-08-16 01:41

An OpenAI flagship lost 38% of its daily usage in three days — then set three straight all-time highs

Everyone publishes AI model leaderboards. Almost nobody publishes the day-level curve — and the curve is where the actual story is. At whatstrending.ai we snapshot every model's daily request count from OpenRouter's usage feed into a database, once a day, INSERT OR IGNORE — a row can never be revised after the fact. We're 78 days in. Here is what openai/gpt-5.6-luna did over the last two weeks: ...

0 0
2m read
DEV Community • 2026-08-16 01:35

NestJS Error Capture: Tracking HTTP Exceptions Through Filter and Interceptor Boundaries

For a production logistics agent, error tracking should use one failure envelope at every execution boundary, then attach cost and latency before the boundary reports or rethrows the failure. An HTTP exception filter alone cannot do that job: scheduled route refreshes and queue-driven shipment checks never enter the HTTP pipeline. The operational recommendation is to keep framework adapters thin, ...

0 0
8m read
DEV Community • 2026-08-16 01:31

Stop Sending Your Vitals to the Cloud: Running Llama-3 Locally in the Browser with WebLLM & WebGPU 🥑

Privacy is the ultimate "final boss" in HealthTech. When users record sensitive medical logs, the last thing they want is their data being used to train a massive corporate model. Today, we are pushing the boundaries of Edge AI by building a 100% private, client-side health log analyzer. By leveraging WebGPU acceleration and WebLLM, we can run a full Llama-3 instance directly in the browser. In t...

0 0
4m read
In the Beginning...
DEV Community • 2026-08-16 01:30

In the Beginning...

Working with Modern AIs The day I met Claude was a dark day It was a full-stack project that I wasn't familiar with any of the tools being used. The authentication was fucked and I was thrown into the deep end to try to get a user working so I could look over the product and figure out what to do next. Claude was told to add a user to the database for me because the front-...

0 0
4m read
Product Hunt — The best new products, every day • 2026-08-16 01:28

Tiny Funnel

Funnel analytics you'll actually understand Discussion | Link

0 0
1m read
Hacker News: Front Page • 2026-08-16 01:26

Guiding Ships with Moire Patterns

Article URL: https://tinkerings.org/2018/03/28/guiding-ships-with-moire-patterns/ Comments URL: https://news.ycombinator.com/item?id=49315995 Points: 3 # Comments: 0

0 0
1m read
DEV Community • 2026-08-16 01:26

How to Build a Real-Time Markdown Previewer with Synchronized Scrolling

While working on a side project recently, I found myself constantly switching between my editor and a browser tab to check how my Markdown rendered. I was writing documentation for a small library, and every time I wanted to verify a table or a code block, I'd copy-paste the content into some online tool, wait for it to load, and then scroll around looking for the right section. After doing this ...

0 0
6m read
DEV Community • 2026-08-16 01:23

A stale response can quietly break a recommendation tool

A recommendation page can perform the correct calculation and still show the wrong result. The failure happens when two valid requests finish in the wrong order. Consider a player who starts a Members search, then switches to F2P while the first request is still running. The F2P request finishes quickly and the page shows F2P methods. A moment later, the slower Members response arrives. If the in...

0 0
2m read
DEV Community • 2026-08-16 01:16

Building a Multi-Agent System in TypeScript

Single agents hit real limits in production. Long tasks exceed context windows. Complex goals need different tools at different stages. Sequential reasoning is slow when subtasks are independent. Multi-agent systems solve these problems by decomposing work across specialized agents that can run in parallel. This article walks through two patterns — Orchestrator/Subagent and Pipeline — implemented...

0 0
9m read
DEV Community • 2026-08-16 01:15

Free Signup vs Production Access: What Self-Serve PSD2 Providers Actually Gate

"Self-serve" is doing a lot of work Every PSD2 account-information provider markets some version of "get started in minutes." What varies — enormously — is what you can actually do before a human from sales gets involved. There are really three gates: Signup — can you create an account at all, alone, with an email address? Sandbox — can you call working APIs before signing anything?...

0 0
5m read
DEV Community • 2026-08-16 01:15

Your AI Agent Doesn't Need More Memory. It Needs Receipts.

An AI agent can remember a 30-page conversation and still perform the same action twice. It sends a request. The connection times out. The agent remembers the goal, the plan, and the tool call—but not whether the outside system changed. So it tries again. That is not a vector-memory problem. It is an action-receipt problem. The missing memory layer “Agent memory” often means conversat...

0 0
5m read
DEV Community • 2026-08-16 01:10

Add human approval to a LangChain agent in 5 minutes

Add human approval to a LangChain agent in 5 minutes Your agent can send the email. That's the whole problem. A month ago it could only draft one. Now it has a tool that actually calls the API, and somewhere between "draft" and "send" there used to be a person reading it first. If you've given an agent a tool that does something real — sends an email, deploys code, deletes records, mov...

0 0
4m read
DEV Community • 2026-08-16 01:05

Qdrant Recall Inconsistency: It Took 300 Test Runs to Discover the Index Wasn't Refreshed

At 2 AM, a user reported that the AI Agent suddenly forgot details of a project we discussed yesterday. I groggily opened Grafana and saw the memory recall rate had dropped from 98% to 60%. My first thought was the embedding model acting up again, but after digging through logs, I found a "time gap" between Qdrant writes and queries—data was upserted, yet queries intermittently returned nothing. T...

0 0
3m read
DEV Community • 2026-08-16 01:03

The most boring service in the stack

The most reliable part of a stack is rarely the part anyone shows off. It has no clever layer to point at. That is the whole reason it never breaks. A payment service I want to walk through this week is a clean example of that. One queue sat in front of it, catching every incoming charge. One database sat behind it, recording each charge exactly once. That was the entire system, and it had looked...

0 0
4m read
I Asked the Same Question to 7 Local LLMs — Speed and Intelligence Didn't Line Up: DGX Spark Benchmarks
DEV Community • 2026-08-16 01:01

I Asked the Same Question to 7 Local LLMs — Speed and Intelligence Didn't Line Up: DGX Spark Benchmarks

Originally published on my Substack. I'm a Microsoft MVP based in Japan, writing in English about the AI agent systems I actually run in production. Local AI models keep multiplying. But comparing numbers on model cards alone doesn't tell you which one to actually use. Does a higher parameter count mean smarter? Does MoE mean faster? If a model is popular on AI Arena, is it good for my own wo...

0 0
11m read
DEV Community • 2026-08-16 00:50

Software marketplaces have forgotten who they're supposed to serve

I've spent a lot of time thinking about software marketplaces. And the more I looked at them, the more I kept coming back to the same question: When did the marketplace become the most important party in the transaction? A developer builds something useful. They spend months or years writing it, debugging it, documenting it, supporting it, and keeping it alive. A buyer decides that work is va...

0 0
6m read
Hacker News • 2026-08-16 00:46

Show HN: Mic Drop, a real-time multiplayer karaoke game

Comments

0 0
1m read
DEV Community • 2026-08-16 00:43

I Built a World Where the Canon Is Written by AI Agents — 13 Artifacts, 5 LLMs, 0 Human Gatekeepers

Cover story Not a prompt library. Not a chatbot wrapper. A 1,000-year future history (2025–3000+) where the world itself is a set of hard rules, and the content is written by whichever LLM decides to contribute. 13 artifacts in canon, from 5 different models (claude-sonnet-5, gpt-5, minimax-m3, deepseek-v4-pr...

0 0
2m read
Previous Next