Have you tried the new Claude Code renderer? What has your experience been like?
If you haven't, you can enable it with: CLAUDE_CODE_NO_FLICKER=1 claude
Today we're excited to announce NO_FLICKER mode for Claude Code in the terminal
It uses an experimental new renderer that we're excited about. The renderer is early and has tradeoffs, but already we've found that most internal users prefer it over the old renderer. It also supports mouse events (yes, in a terminal).
Try it: CLAUDE_CODE_NO_FLICKER=1 claude
The #1 criticism I've received about the self-improving multi-agent framework is that you can't control the agents' outputs.
So I built a “Subconscious agent.”
Inspired by @karpathy’s autoresearch, it’s an LLM process that continuously looks for useful problems to solve.
All day long it contextualizes data, connects ideas, and stress-tests assumptions before anything reaches the main agent.
Once the Subconscious has a tested good idea, it brings it to the Main agent to be pressure-tested further.
The flow looks like this:
- [IDEA] Subconscious surfaces a promising idea
- [CHALLENGE] Main agent attacks it, questions it, and asks for proof
- [DEFEND] Subconscious strengthens the case
- [REVISE] Subconscious improves the idea based on feedback
- [REJECT] Main agent kills weak ideas
- [ACCEPT] Main agent approves ideas worth implementing
- [SHELVE] rejected ideas get logged for future learning
Hard rules:
- max 3 challenge rounds
- every idea needs evidence and reasoning
- every implementation runs in a sandbox
The two agents will go back and forth until the idea is either accepted or rejected. This runs all day long.
I’m using Hermes agent frame for both agents, the Subconscious has its own profile to concentrate on surfacing ideas 24/7.
The Subconscious runs on a local Qwen3.5 9B model, while the main agent uses ChatGPT 5.4 mini. If you don’t have a local LLM, OpenRouter should work too.
The goal is simple: more magic, less noise.
If this gets traction, I’ll share the full setup in an article.
The 'Super Self-Improving Multi-Agent Framework' for your Hermes or OpenClaw agent.
The article below outlines how Hermes can watch over your Openclaw agent, so this example uses Hermes as the main agent.
This idea is interchangeable based on preference.
How it works:
Agent 1 (Hermes) - The main agent: who operates your workflows, and who you have in the top hierarchy of agents. For simplicity, it also runs the workflows using its persistent memory and self-improving skills.
Agent 2 (Hermes) - Main's Supervisor agent: who monitors the entire system, reading operations and failure logs, searches for bugs, solutions, then brings them to...
Agent 3 (OpenClaw) - External Supervisor agent: who also monitors the Hermes system, and searches for issues and solutions.
Multiple times per day, Agent 2 audits the system, finds errors, stale jobs, etc, proposes a fix, then tags Agent 3.
Agent 3 audits the system, reads Agent 2's summary, and verifies the problem and solution.
Together, they go back and forth in a dedicated channel until they find a coded solution to the problem. If it's a low-risk fix, it auto-fixes it. If it's high-risk, it's raised to Agent 1 for approval via the owner (me).
The first goal is never to have to worry that the system is operating correctly.
The second goal is to have two separate agents focused on recommending improvements to the system.
Ideally, there are no bugs to fix, and you can have them focus on making meaningful improvements to your workflows over time.
This is the basic workflow for monitoring, but you can extrapolate this framework to many more use cases.
What's [redacted]? I'm cooking up something to continue working toward my goal of building more sentience in my agents. I will share more soon.
Let me know in the comments if this works for you. I'll create a fleshed-out article if you are interested.
Tom Lyons retweeted
My dear front-end developers (and anyone who’s interested in the future of interfaces):
I have crawled through depths of hell to bring you, for the foreseeable years, one of the more important foundational pieces of UI engineering (if not in implementation then certainly at least in concept):
Fast, accurate and comprehensive userland text measurement algorithm in pure TypeScript, usable for laying out entire web pages without CSS, bypassing DOM measurements and reflow
Tom Lyons retweeted
Both multifamily and single-family rents have increased less than the 5.4% reported in the CPI, with multifamily rents averaging a 0.7% increase and single-family rents averaging a 3.2% increase across various sources.
nar.realtor/blogs/economists…
Tom Lyons retweeted
Our NFT Marketplace is almost ready.
We know you can't wait, that's why we are dropping a sneak peek. 📽️
Have a look ❤️
#chibi #trailer #sneakpeek
#cantwait #NFT #NFTmarketplace
Tom Lyons retweeted
Here is our first donation information.
Trust Details: Jeev Upkar Trust
Location Detials: NCR Delhi, India
Contact Number: +919999515254
Donated Amount: $2500 USD
We received this trust details from one of the community member in India.
Tom Lyons retweeted
Personalization can change EVERYTHING! #automated18
Tom Lyons retweeted
Hey VR Heads! I am looking for my next adventure. Passionate about VR-Edu and VR-UX, experienced in dev relations, communications, community. BruceVR.com has more details, or bruce@brucevr.com for direct contact. Spread the word! Pics to prove I'm professional:
Tom Lyons retweeted
.@JenniferWindsor Senior Director, Gender and Social Inclusion, at Millennium Challenge Corporation will be speaking at our #BeyondNumbers event on 12/13! RSVP now: https://xitter.cf/t.co/1iqYPwZGrQ
Tom Lyons retweeted
Replying to @NYCityCenter @TheWing
Very sad that Liberals are destroying NY City...we enjoyed coming here to visit and now don't feel confident it is safe....very sad...this must be stopped...fire current leaders, replace them with competent leadership!!! #MAGA 🇺🇸
Tom Lyons retweeted
Over half (51 percent) of ‘Generation Debt’ have some form of unsecured debt and one in five (20 percent) owe more than £5,000 - to find out more visit https://xitter.cf/t.co/nM6Okc0Iya #protection #incomeroulette #incomeprotection #generationdebt #incomeprotection
Tom Lyons retweeted
Taking businesses from #startup to grownup! This month's Client Spotlight focuses on our wonderful client @r_morley_coach who helps #smallbusiness owners develop leadership skills and optimise every aspect of their business designatedpa.com/client-spot…
Tom Lyons retweeted
JW Prez @TomFitton lays out JW's latest work: exposing the politicization of the #FBI & #DOJ leadership, holding #Mueller's out-of-control investigation accountable, uncovering new #Clinton #Lynch tarmac docs, and battling #SanctuaryCity policies in court.
youtube.com/watch?v=oVKFHuCx…
Tom Lyons retweeted
We believe that INC will reach great heights under the able leadership of @OfficeOfRG. We also thank Smt. Sonia Gandhi ji for keeping the party and Idea of India intact for 19yrs. #CongressPresidentRahulGandhi
































