don't sleep on @tanaysingh789, super talented, and just getting started

Stop manually making flowcharts. Try this GitHub skill with Claude Code. I found an open-source tool that turns a plain description of a software system into a clean, interactive diagram. It's called Archify, and it has more than 66,000 stars on GitHub. You add it as a skill to an AI coding agent like Claude Code, Codex, Cursor, or OpenCode. Then you describe the system in the chat in one line. Archify turns that line into a single HTML file you can open, click through, and send to anyone. If you point your agent at an existing codebase, it reads the code and Archify maps how the pieces connect. I liked five things about it. 1. It makes five kinds of diagrams, including system maps and step-by-step workflows. 2. You can click any piece and trace what connects to it. 3. It checks the layout before it hands the diagram over, so arrows don't pile up and labels don't overlap. 4. It has dark and light themes and exports to PNG, SVG, or a short video. 5. You keep editing in plain chat, with requests like "add Redis" or "highlight the rollback path." You don't need a codebase to use it. A description in the chat is enough.

JEV is INSANE. We gave it 400 companies and one candidate profile. In 12 seconds, it predicted which jobs the candidate had the highest chance of getting, assigned a confidence score and detected job-candidate mismatches. All for just $0.0005 It can also score companies, analyse your experience, match you with the right roles and identify the opportunities you’re most likely to get based on your profile. Coming soon to @textbackdoor Comment “JEV” for early access.

Playing with Jev adapter for Codex @CompleteSkeptic @sama @elonmusk - this should be the default. Current computer / browser use is a tad slow. Lots of improvement here - from cutting the subagent handoff time to warm up time and improving the loop itself - but i think i got it to a working state. Jev is an absolute unlock

github.com/githubnext/localj… Not everyone on the team has access to Jev yet. Spent a morning cobbling together a poor man's Jev on top of omlx for local use. Benchmarked and eval'ed a variety of models including diffusiongemma and a variety of autoregressive models (Qwen MoE, Gemma 4 MoE, and Gemma 4 e4b/e2b.) Benchmark report is in the repo. This is 100% promptcoding but hey the evals look okay, speeds are pretty good on local machine (m5 max 64gb), and the LocalJev server exposes an API that can be used with the normal Jev API wrapper libraries.

jev is insane 🤯 Here is Jev playing subway surfers at super human speed, and also playing 50 games at once. cost less than a cent to do this run. Jev does not replace llms like astra or fable, but opens up an entirely new world of capabilities.

STOP ASKING YOUR WIFE "HOW WAS YOUR DAY" she will say "fine" every single time replace it with this instead: “analyze your day and find the top 3 largest inefficiencies, then create proactive agentic workflows that will fix them. make no mistakes”

GPT-6 ASTRA TURNED $240 INTO $2,860. THEN IT LOCKED MOST OF THE MONEY AWAY FROM ITS OWN TRADING AGENTS. four sessions into the experiment, i opened the trading wallet. $895. the report said $2,860. i refreshed both screens, convinced something had gone wrong. then i opened the transfers. $1,965 had moved into a separate reserve wallet. every transfer had a receipt. the numbers matched to the cent. the desk had four jobs. three agents handled discovery, contract checks and execution. the fourth was called CASHIER. CASHIER watched settled results. after each profitable session, it moved 75% of the net gain into reserve. the trading agents could see that balance. their permissions gave them no way to pull it back. that detail suddenly became very interesting to me. i started calculating what the next position could look like with the whole $2,860 available. opened the settings. hovered over the allocation. then closed them. the next session was ugly. two positions closed red. working capital dropped from $895 to $731.40. i watched the desk reduce its next order and keep scanning. the reserve still read $1,965. that was the first time the setup made sense emotionally. a bad session had a smaller pile of money available to damage. i spent another hour reading the logs. the least exciting agent on the desk had done the thing i was most likely to postpone. it had actually taken the money off the table. CASHIER never found a single winning token. it was the first agent i decided to keep.

Codex tip: A cost-efficient Luna + Sol agent tree, orchestrated by Astra. Effort levels chosen by weighing DeepSWE’s pass rates, average cost per task, and agent steps. Hand this to Codex to set it up 👇

GPT-6 Astra builds the most powerful trading agents i wrote a 6-page research paper on exactly how to find profitable strategies 24/7 with Astra, along with the COMPLETE CODEBASE here is how you set it up: 1. the 4 mispricing categories every hedge fund actually hunts (statistical arbitrage, volatility surface, factor decomposition, insider clusters) with the exact formulas for each 2. the 8 bot architecture that maps to every function of a real fund, one bot per role, with maker checker separation so nothing grades its own output 3. the 300 agent monitoring layer that watches order books, options flow, SEC filings, macro releases, and central bank X accounts in parallel 4. the hypothesis generator that reads filtered candidates and codes new strategies every night in Python, backtests them, and throws out anything below Sharpe 1.5 5. the exact validation thresholds every strategy has to pass before deployment. Sharpe above 1.5, drawdown below 15%, hit rate above 55%, t stat above 2.0 6. the Telegram alerts that ping your phone with instrument, strategy, confidence score, Sharpe, drawdown, action window, and Kelly sized position this is the exact system I have been running for the past 3 days:

astra is almost TOO good at coding. it accounts for more edge cases than i’m interested in maintaining 😂 the challenge now is communicating which tradeoffs you’re willing to make and how much complexity you want

Harness-as-a-Service OAI’s Agents API is managed Codex offered as an endpoint - the final form of many products will converge to this form factor was clear last year that as agents got better at autonomous work, ppl would offer their agent as an endpoint for completing work if you look hard, many features/products expose a Harness for a specific task, ex: Gemini’s Agentic Video Understanding we’re in a Model-Harness product optimization cycle of - product need - build a harness that optimizes a model to do it - if it works well, fine-tune this behavior directly into a model this UX of managed agents + pipeline of fine-tuning vertical capabilities into models after discovering them through harness engineering will continue to lead the way for the next year or so

Open-source Agent Orchestrator for planning, running, and supervising coding agents. github.com/Untrivial-ai/agen…

GPT-6 Astra is state-of-the-art on FrontierMath Tier 4, ARC-AGI 3, and TerminalBench-4.0. GPT‑6 Astra is also a major advance for scientific discovery, with state-of-the-art performance on Terminal-Bench Science 0.1 and HealthBench Pro.

Philadelphia builders—this one’s for you. 🤖 @quirq_ai is sponsoring a track at the AI Agent Hackathon on Sunday, September 20, at @PennovationWork in Philadelphia. Spend the day building and experimenting with: • Coding agents • Multi-agent workflows • Tool use and automation • Agent memory and context • Evals and reliability • Open-source agent frameworks Compete solo, bring a team, or meet collaborators at the event. Join us on September 20. Register: luma.com/muz8cqhd #AIAgents #Hackathon #PhiladelphiaTech #AgenticAI #SoftwareEngineering #OpenSource #PhillyTech

What a turnout yesterday for Claude Code Philly! 🤖💻 We spent the afternoon at Turkish Brew connecting, coding, sharing ideas, and enjoying authentic Turkish and Mediterranean cuisine. The room brought together an incredible mix of people: ☕ Business owners 🌎 Climate engineers 🔐 Security engineers 📊 Business analysts ⚙️ Embedded systems engineers 📱 Mobile developers 💻 And builders from across the broader tech community Some people even traveled all the way from Baltimore just to spend a casual Saturday building with us in Philadelphia! We met new collaborators, and enjoyed exactly the kind of relaxed weekend energy we want these gatherings to create: laptops open, coffee flowing, great food, and interesting conversations happening throughout the room. Thank you to everyone who joined us—and to Turkish Brew for hosting us! We’ll be back for another Claude Code Philly session soon. 🔗 lnkd.in/eHmwx-gq #ClaudeCode #PhiladelphiaTech #PhillyTech #CodeAndCoffee #SoftwareEngineering #AIEngineering #DeveloperCommunity #Anthropic #CommunityBuilding

I love how people have started coming up to me as "Hey I'm Human John", or "Hey I'm Human Michael". Maybe the start of a trend ahah

big news! 🥳 got into YC solo founder with $40k monthly revenue! building Thomas: the first YC-backed AI founder (yep, we cloned myself) Thomas is a virtual human who starts, runs, and grows his own companies. His only goal is to make money. Once launched, he works forever toward that goal. More info in the first comment! And about YC: just as wonderful as I expected, very lucky to have @dessaigne and @collinmathilde as partners. More soon 🙌🥳

We started out as a gateway, we’re becoming a harness of harnesses, and soon we’ll be all your AI needs in one place.

got @MentraGlass in. time to test them out and run @kyra_interface software on them. first impression - they are hella comfortable. i might actually replace my meta raybans