4/ Why @ego_agent outperforms headless setups: → Shares your active Chrome state to skip auth loops.
→ Semantic snapshots read deeply nested iframes without̀ hallucinating. A TRUE first-class runtime for AI, not an afterthought. → https://
lite.ego.app macOS. 100% FREE.
@datachaz
-
Ego Agent: AI runtime outperforming headless setups for seamless automation
By
–
-
Custom Chromium browser compresses HTML to 400 tokens for LLM
By
–
DUMPING 30K TOKENS OF RAW HTML INTO AN LLM RUINS CONTEXT AND BURNS API LIMITS.
— Charly Wargnier (@DataChaz) 1 juin 2026
🚨 @ego_agent just fixed this.
It is a custom Chromium browser where agents read a compressed 400-token tree in parallel background Spaces.
macOS. 100% FREE 🧵↓ pic.twitter.com/rEfzu2XgjiDUMPING 30K TOKENS OF RAW HTML INTO AN LLM RUINS CONTEXT AND BURNS API LIMITS. @ego_agent just fixed this. It is a custom Chromium browser where agents read a compressed 400-token tree in parallel background Spaces. macOS. 100% FREE ↓
-
NVIDIA accelerates bounding box detection 10x by removing mandatory token prediction
By
–
🚨 NVIDIA just pulled off something crazy: making bounding box detection 10x faster by ripping out the exact step the entire industry assumed was mandatory ↓
— Charly Wargnier (@DataChaz) 1 juin 2026
Every VLM grounding model treats boxes like sentences, predicting them token by token. It’s inherently slow.
Enter… pic.twitter.com/OE7fxZFF4VNVIDIA just pulled off something crazy: making bounding box detection 10x faster by ripping out the exact step the entire industry assumed was mandatory ↓ Every VLM grounding model treats boxes like sentences, predicting them token by token. It’s inherently slow. Enter
-
Harness changes boost SWE-agent; Life-Harness confirms patching improvement
By
–
When SWE-agent got a 64% lift from interface changes, @rohit4verse
's "The Harness Is Everything" (1.3M views) explained why. Life-Harness proves it again: 116/126 setups improved patching just the harness. Frozen models saw an 88.5% mean lift across 18 backbones. how it works: -
Build Autonomous Claude Code Routines in 15 Mins with Anthropic Engineer’s Guide
By
–
This Anthropic engineer reveals how to build rad Claude Code Routines in 15 mins.
— Charly Wargnier (@DataChaz) 31 mai 2026
The result?
A 24/7 autonomous coding partner.
Along with @zodchiii's guide, you'll automate 50% of your workload with Claude Code.
No fluff. Just the playbook from the ppl who actually built it. https://t.co/b9b0dzFvb2 pic.twitter.com/LG0Vro1Gt5This Anthropic engineer reveals how to build rad Claude Code Routines in 15 mins. The result? A 24/7 autonomous coding partner. Along with @zodchiii
's guide, you'll automate 50% of your workload with Claude Code. No fluff. Just the playbook from the ppl who actually built it. -
Open-sourced Hermes Agent Web UI: Full terminal parity, lightweight, 3-panel design.
By
–
THIS GUY LITERALLY OPEN SOURCED A FULL WEB UI FOR HERMES AGENT and the feature set is insane. You now get 1:1 terminal parity right in your browser. The UI is lightweight: zero build steps and a sleek 3-panel layout for chat, sessions, and file browsing. But why Hermes?
-
245% Faster Claim: Dropping Step-by-Step Tool Calls for Full JS Functions
By
–
245% faster is a massive claim, but dropping clunky step-by-step tool calls for full JS functions makes a lot of sense! Testing it rn, will report back 🙂
-
245% faster JS function execution: a promising new approach
By
–
Claiming 245% faster completion is a big statement, but their approach of running full JS functions instead of step-by-step tool calls makes a lot of sense!
— Charly Wargnier (@DataChaz) 30 mai 2026
Going to have to try this 👀 https://t.co/TE7DdyHXN1Claiming 245% faster completion is a big statement, but their approach of running full JS functions instead of step-by-step tool calls makes a lot of sense! Going to have to try this
-
Dynamic workflow execution with subagents (Claude Code)
By
–
ANTHROPIC JUST DROPPED A MASSIVE UPDATE FOR CLAUDE CODE: DYNAMIC WORKFLOWS. Instead of a single pass, Claude can now write an orchestration script on the fly and spin up tens to hundreds of parallel subagents for complex tasks ↓ First, they divide the work, run
-
Google launches free 5-day vibe coding AI course
By
–
GOOGLE JUST DROPPED A BRAND NEW, FREE 5-DAY VIBE CODING COURSE Classes kick off on June 15th, so now’s the perfect time to register and get ready for Day 1. Google's first AI Agents course last year drew in 1.5 Million learners. Now, they’re launching the highly anticipated