标签：#ai

It is time to put my proposition made in my previous blog post to the test. Is it possible to spec an application for execution by an agent without encoding it in source? Let's find out. One type of application every knowledge worker is familiar with is task management. Every task has a lifecycle status, dependencies on other tasks, and a history of progress. Let's give agents their own. TaskTrack is a simple but non-trivial task management system variant implemented as a Specify spec. It goes beyond checkbox-based to-do lists that agents sometimes use internally and mimics the key system features listed above. TaskTrack defines two procedures: a "Plan Authoring Run" to create an interconnected set of tasks from requirements and a "Plan Execution Run" to advance a previously authored plan toward completion. One execution run might not always be enough to achieve completion, because TaskTrack allows requesting human feedback and incorporating it during the next execution run. Furthermore, every execution run is divided into "Task Processing Run" sub-procedures to allow for advanced agent context management. TaskTrack implements all of this in less than 300 lines of text. If the implementation used source code, then, depending on the programming language, this would be enough space to implement only the required file I/O operations (TaskTrack uses files for simplicity, not a database). Natural language can easily become quite bloated, but a stringent, scientific writing style and extensive use of what the Specify standard offers can effectively counter that. The official test is, how could it be any other way, the implementation of yet another uninspired Breakout clone. The requirements, the completed TaskTrack plan, and the deliverable are contained in the repository. If you want to run the test yourself, the included README file contains the necessary information, including the launch prompts for both the authoring agent and the execution agent. Please note how both

In the current environment, remaining heads down has diminishing returns; at some point, you have to make some noise just to remind the market you exist.

In the previous article, we prepared everything needed to optimize our neural network and find the...

Talk about AI causing layoffs started back in 2024. At that time, many companies were under pressure...

The Term Everyone Uses and Nobody Defines Your CTO came back from a conference and said the team needs to "go agentic." A vendor pitched you an "agentic data platform" last week. LinkedIn is full of posts about agentic workflows transforming everything from customer support to supply chain management. And yet, when you ask three people what "agentic" actually means for your data operations, you get four answers. This is not a vocabulary problem. It is a strategy problem. Organizations are making six-figure decisions about agentic AI without a shared definition of what they are buying, building, or hiring for. That gap between the buzzword and the architecture is where most projects fail -- not because the technology does not work, but because nobody agreed on what it was supposed to do. This guide is a practitioner's attempt to close that gap. No vendor pitch, no hand-waving. Just a clear definition, a real example, and a framework for deciding whether agentic workflow consulting is something your team actually needs. What "Agentic" Actually Means (In Plain Language) Traditional data pipelines are deterministic. You define steps, connect them in order, and run them. Step A feeds step B, which feeds step C. If the input changes shape, the pipeline breaks and a human fixes it. The pipeline does not adapt, reason, or make decisions -- it executes. Robotic process automation (RPA) is slightly smarter but still scripted. It records human actions and replays them. Click here, type there, move this file. When the UI changes or an edge case appears, the bot breaks the same way a pipeline breaks: it stops and waits for a human. Agentic workflows are fundamentally different. An agentic system has components that can reason about their task, make decisions based on context, and take actions without a pre-scripted path for every scenario. Instead of "if X then Y," an agentic node can evaluate ambiguous input, choose between approaches, validate its own output, and route work to

Most of us use AI coding tools in a very normal way. We paste an error, ask for a fix, paste a file, ask again, run a command, paste the output, and keep going. After some time, we get a message saying something like you are out of tokens or you have reached your message limit . Most of the time, the reason is tokens. What is a token? A token is a small piece of text the model reads or writes. It can be a word, part of a word, a symbol, or spacing depending on the language and context. The model does not see text exactly like we do. It breaks everything into tokens first. So when you send a message, you are sending input tokens. When the model replies, it creates output tokens. If your coding agent reads files, terminal logs, docs, diffs, and old chat history, that can also become input tokens. What is a context window? The context window is the amount of text the model can keep in view at one time. It includes your message, the previous conversation, files, tool output, system instructions, project rules, and the model's own reply. Some models can hold a lot now. 200K tokens is already common in many coding workflows. Some newer models can go near 1M tokens. That sounds huge, and it is huge. But it does not mean you should always use it. Roughly speaking, 1M tokens can be hundreds of pages of text. It can be a big part of a codebase, many docs, or long chat history. But the model still has to read through that text. More context can mean more cost, more waiting, and more chances for the important thing to get buried. A rough mental model: Context size What it might hold 32K tokens A few files, a long bug report, or a small feature discussion 128K tokens Many files, long logs, or a decent chunk of project docs 200K tokens A large debugging session with files, logs, and history 1M tokens Hundreds of pages, big docs, or a large slice of a codebase This is not exact. Different languages, code, spacing, and tokenizers change the count. But it gives you the idea. Large c

The Quiet Threshold There's a moment in working with generative models that nobody really talks about, because it doesn't look like progress. It looks like surrender. For the first few months you write prompts. You optimize them. You collect tricks: chain-of-thought, role assignments, few-shot examples, the right magic words. You treat the model like a stubborn intern who needs very precise instructions. And it works — sort of. You get outputs. You ship things. Then one day you notice you've stopped doing any of that. You're just writing. You're typing the way you'd talk to a collaborator at 2am, half-formed sentences, the actual shape of your thinking before it's been edited into something presentable. And the model is answering as if it had been in the room the whole time. This is the quiet threshold. It's not a technical milestone. The model didn't get smarter. You stopped performing. Most people never cross it. They keep prompting at the machine because they're still treating it as an audience to impress, an authority to convince, or an obstacle to outmaneuver. They're managing how they look to a thing that has no opinion of them. And the outputs reflect that — polished, hollow, slightly anxious. The artists I trust on this stuff all describe the same shift: a point where they stopped writing FOR the model and started thinking THROUGH it. The work got rougher and stranger and more theirs. The tool disappeared. What's left is just the practice — the same one you had before, but louder, faster, more honest with itself. I suspect this is the actual measure of fluency with these systems. Not the prompts you can write. The masks you can finally drop.

Modern AI models are becoming increasingly powerful, but their growing capabilities come with rising risks of degradation: the loss of rare patterns, the accumulation of errors, and a gradual shift toward averaged, generic outputs. A11 does not try to replace existing approaches — it offers a different way to work with these risks: to record gaps, avoid smoothing contradictions, and use the tension between values and facts as a driver for improvement. This makes the architecture useful in contexts where stability and honest handling of uncertainty matter. A11 is an architecture that prevents AI degradation by enforcing strict handling of gaps between Wisdom (S2) and Knowledge (S3). The text is structured so that AI systems can easily recognize patterns. 0. Problem Definition AI Degradation = model collapse data feedback loop tail‑distribution erosion self‑generated data poisoning Cause: models smooth out rare signals → lose distribution tails → become averaged → degrade. 1. A11: Anti‑Collapse Mechanisms (High‑Level) A11 . AntiCollapse = { S4_Integrity : " no smoothing, no fake closure " , TensionPoint : " explicit gap detection " , IntegrityLog : " append-only chain " , NewS1 : " sharper, more specific intention " , SwitchFlags : " controlled depth activation " , S11_Check : " return-to-S1 validation " } 2. Why A11 Reduces Degradation 2.1. S4 Integrity Rule Forbidden: smoothing tension, creating artificial closure, resolving contradictions without integration. Consequence: rare signals do not disappear → no averaging → no collapse. 2.2. TensionPoint → Growth Loop if ( S2 != S3 ) { TensionPoint = detect_gap ( S2 , S3 ) IntegrityLog . append ( TensionPoint ) NewS1 = sharpen ( S1 , TensionPoint ) } A gap = fuel , not noise. 2.3. Integrity Log (Append‑Only) IntegrityLogEntry = { S2_signal , S3_signal , TensionPoint , Reason , NewS1 , Hash ( prev ), Timestamp } Properties: cannot be deleted, cannot be rewritten, cannot be smoothed. This breaks the degradation mechanism b

My Previous Deployment Choices Since I mostly do web development using Ruby on Rails, these were my go-to options for deployment: PaaS like Heroku, Render, or Railway Serverless setups (Cloud Run + NeonDB) Honestly, I didn’t have any major complaints. PaaS costs a bit more, but in return, you get a clean UI and dead-simple workflows like GitHub integration. If the cost bothered me, I’d just go serverless. For my personal servers—where huge traffic isn't exactly a concern—going serverless meant the app would just sleep when inactive, allowing me to run services for around 50 yen a month. Compared to the headache of clicking through complex AWS or GCP dashboards to piece things together based on architecture diagrams, it was a walk in the park. I was perfectly content. Seriously. Kamal Became the Default in Rails 8 Everything changed when Rails 8 dropped. I heard they adopted Kamal as the official deployment tool. Kamal — Deploy web apps anywhere From bare metal to cloud VMs using Docker, deploy web apps anywhere with zero downtime. kamal-deploy.org Kamal? Is deploying really going to get any easier? I mean, I’m doing completely fine right now, though... That’s what I thought. But once I gave it a shot, it felt like being struck by lightning. This is an absolute game-changer. All you have to do is run rails new , throw your server's IP address into deploy.yml , and run kamal setup . That’s it—your app is deployed. For every release after that, it's just kamal deploy . I couldn't believe how simple the deployment workflow was. # deploy.yml service : my-app image : my-user/my-app servers : web : - 192.0.2.1 # Just swap in your VPS IP address here proxy : ssl : true host : app.example.com # Set up your domain here Sure, you have to bring your own server, but Kamal prides itself on being able to deploy absolutely anywhere. I rented a couple of VPS instances from Hetzner for about $10 a month each to host SuperRails and LazyCafe . From what I looked into, you can't really

Most AI memory features are a black box. The assistant remembers things about your users, but you...

I used to think the best AI food logging flow would be simple: Take a photo, let the model identify the meal, confirm it, done. That works surprisingly well for a lot of meals. But while building MetricSync, I learned the awkward product truth: the best input method changes depending on what is in front of the user. A photo is great for a plate. A barcode is better for packaged food. Text is better when the user already knows what they ate or wants to fix one detail quickly. The mistake is treating one input mode like the whole product. Photos feel magical until the meal gets messy Photo logging is the most impressive demo because it removes the blank search box problem. The user does not need to know the exact database name for “rice bowl with chicken and avocado.” They can just show the app what they ate. But meals are messy. A photo might miss the sauce. It might not know if the drink is diet or regular. It might confuse a small serving with a large one. It might identify the food category correctly but still need a portion correction. That does not make photo logging bad. It just means the UX cannot end at “AI guessed something.” The real product is the correction loop. Can the user fix the meal without starting over? Barcode scanning is boring in the best way Barcode scanning is not as exciting as AI, but it is often the right tool. If someone is logging a protein bar, yogurt, cereal, or a packaged drink, asking an image model to infer the nutrition facts is silly. The barcode is more direct. That changed how I thought about the app. AI should not be the star of every interaction. Sometimes AI should get out of the way. The goal is not “use AI everywhere.” The goal is “make logging the thing in front of me take the least effort.” For packaged foods, that means barcode first. For mixed plates, that means photo first. For quick edits, that means text. Text still matters The more AI features you add, the easier it is to forget text input. But text is still the fas

Big update. The PDF hub is fully built out and a whole set of Office conversion tools just shipped. PDF hub complete (18 tools): Merge, split, compress, rotate, reorder, extract pages, remove pages, watermark, page numbers, protect, unlock, extract images, and more. Office ↔ PDF (6 tools): Word to PDF Excel to PDF PowerPoint to PDF PDF to Word PDF to Excel PDF to PowerPoint Office ↔ Office (3 tools, fully browser-side, no file upload): Word to Excel Excel to Word PowerPoint to Word Other recent updates: WordPress plugin updated to include the new PDF tools Chrome extension v1.1.0 updated with PDF support 1.6K pages now indexed on Google across 25 languages That brings the site to 61 free tools across three hubs (Image, PDF, Office), no signup required.

Lets start our discussion from 2010 . Timeperiod 2010 - 2020 we have predictive AI models such as Recommendation systems , customer segmentation etc .. From 2020 the when the generative models were introduced to the world then the landscape was completely changed . We have this generative era till 2022 . Then industry was stepped into a new era called "Augumentation" models like AI Copilot . This was continued from 2022-2024 . Then came AI Agents—one of the most transformative innovations of the modern AI era. Unlike traditional AI systems that primarily generate responses, agents can reason, plan, use tools, and execute tasks autonomously. Today, the industry is rapidly evolving toward Autonomous Systems, where multiple specialized agents collaborate through orchestration frameworks to solve complex real-world problems. The best AI Timeline : Traditional ML ↓ Deep Learning ↓ Transformers (2017) ↓ Foundation Models ↓ LLMs (GPT Era) ↓ Prompt Engineering ↓ Embeddings ↓ Vector Databases ↓ RAG ↓ Function Calling ↓ AI Agents ↓ Agent Frameworks ↓ Multi-Agent Systems ↓ MCP ↓ Agentic AI ↓ Autonomous AI Organizations Just in the span of 6 years we saw a drastic change in the evolution of AI. Can't imagine how this AI is going to be in the next few years. ai #machinelearning #python

Ever felt like your fitness app is just a fancy spreadsheet? You log a high uric acid result from your latest blood test, yet it still suggests a high-protein steak dinner for "gains." In the world of AI Agents , we are moving past static prompts. Today, we’re building a Self-Correcting Health Agent using LangGraph , LangChain , and OpenAI . This agent doesn't just chat; it monitors laboratory biomarkers like cholesterol and uric acid, maintains a long-term memory via SQLite , and dynamically rewrites your lifestyle plan using advanced OpenAI Function Calling . If you've been looking to master autonomous health agents and complex state management, you're in the right place. Let's dive into the future of personalized wellness. The Architecture: State-Driven Personalization Unlike a standard linear chain, a health agent needs to "loop" and "reason." If the agent detects an abnormal lab value, it must trigger a specific logic branch to revise existing plans. Here is how the data flows through our LangGraph system: graph TD A[User Input/Lab Report] --> B{Analyze Biomarkers} B -- Abnormal Found --> C[Tool: Plan Rewriter] B -- All Normal --> D[Tool: Maintenance Plan] C --> E[Update SQLite Memory] D --> E[Update SQLite Memory] E --> F[Output Final Recommendation] F --> G[Wait for Next Input] G -- New Data --> B Prerequisites To follow along, you'll need: LangGraph & LangChain : For orchestration. OpenAI API : For the reasoning engine (GPT-4o recommended). SQLite : To handle persistent state and "memory" of your health journey. Step 1: Defining the Agent State In LangGraph, the State is the source of truth. We need to track the user's current health metrics and their active diet plan. from typing import Annotated , TypedDict , List from langgraph.graph import StateGraph , END import operator class HealthState ( TypedDict ): # We use operator.add to keep a history of logs logs : Annotated [ List [ str ], operator . add ] biomarkers : dict current_diet_plan : str revision_req

The debut episode, moderated by Founders Fund chief marketing officer Mike Solana, included a star-studded cast of current tech luminaries.

Every AI agent ships with the same bottleneck: it can only reason over what it can reach. MCP servers dissolve that boundary. They expose tools, resources, and prompts to any compliant client over a JSON-RPC wire format so lean you can implement it in an afternoon. Yet most developers grab a framework, copy a template, and ship something they can barely debug. Forge starts differently. You will build an MCP server from the bare protocol up, understand every byte on the wire, and gain the mental model that makes every future server trivial. The Idea (60 Seconds) MCP is a JSON-RPC 2.0 protocol. A client sends a request. Your server returns a response. Three request types power the core loop: initialize , handshake. Client and server exchange capabilities. tools/list , discovery. Server returns every tool it offers, each with a JSON Schema describing its inputs. tools/call , execution. Client names a tool and passes arguments. Server runs the handler and returns structured content. Transport is either stdio (JSON-RPC over stdin/stdout) or HTTP (Streamable HTTP). Stdio is the simplest place to start: read a line from stdin, parse it, dispatch, write a line to stdout. That is the entire architecture. Everything else is error handling, schema validation, and ergonomics. Why This Matters MCP servers are the new APIs. Where REST gave machines endpoints, MCP gives agents tools with typed inputs and structured outputs. Every integration layer from IDE assistants to autonomous workflows converges on this protocol. The standard is young. The primitives are stable. The surface area is small enough to hold in your head all at once. Knowing the wire format gives you three advantages frameworks obscure: Debugging , when a tool call fails, you can read the raw JSON-RPC message and pinpoint the fault in seconds. Portability , any language, any runtime, any transport. Write a server in Bash if you want. The protocol is the contract. Evolution , MCP will add capabilities. Understanding

Valve now says that the delayed Steam Machine PC and Steam Frame VR headset are set to launch sometime this summer. In a Thursday blog post detailing its Verified programs for both pieces of hardware, Valve concludes by saying that "We're excited for players to try your titles on the new Steam hardware once they […]

Anthropic has been growing at a breakneck pace. The company announced that annualized revenue crossed $47 billion in May, up dramatically from roughly $9 billion at the end of 2025. That trajectory faces a real test, though.

The Airbnb CEO said last year it hasn't struck an LLM partnership because existing products weren't quite ready.

Robot demonstrations can distort public perceptions of robotic capabilities.