
@AIMngt Founder @blochainiu Co-Founder @MIT Quant. @Harvard AgenticAl @NFLFlag 2x🏆 24/7 #Optimization
Miami, FL
Joined July 2018
- Tweets409
- Following809
- Followers79
- Likes1.7K
Optinuss retweeted
Fable 5.5 probably definitely tomorrow.
Rumors:
- Better at reasoning and intuition
- Infers intent rather than taking instructions literally
- More ambitious. Ask it to fix a bug and it fixes the deeper root cause
- Does creative, “out-of-the-box” thinking
- Can invent algos to predict stocks
- Bestows complete and eternal enlightenment on first response
AND I’d bet it has major efficiency gains like Opus 5.5. Icing on the cake would be usage for all subs.
Prepare yourself in mind, body and spirit.
ai technical cheat sheet and token pricing calculator. Dynamic slide deck presentation. #AI #Engineering #Tech #CS #LLM
claude.ai/artifact/8x6eoGKfK…
31
Optinuss retweeted
REA is the most dangerous repo on GitHub right now
It gives your AI agent a real disassembler, so it reads any app down to the binary
Every claim comes back with the address behind it
I broke down the exact 8 steps:
Optinuss retweeted
Delete your CLAUDE.md. Not edit it, not trim it, delete the whole file, along with your skills and your hooks, and see what the model does without them. That's Boris Cherny's actual advice from a recent YC appearance, and the Claude Code team has apparently followed it internally enough times that roughly 80% of their own system prompts are gone. His reasoning: most of those rules patched a weakness in whatever model you ran six or twelve months ago. Newer models often don't have that weakness anymore, so the instruction that used to help is now just constraining a more capable model for no reason. His method is almost embarrassingly plain. Delete everything, work normally for a while, watch where the model actually goes off track, add back exactly one instruction when a mistake repeats, and run the whole cycle again at the next major model release. Keep security and compliance rules. Keep the project quirks a model genuinely can't infer from reading the code. Cut folder structures, dependency lists, and architecture summaries, since a capable model can read those off the repo itself faster than it can read your stale description of them.
This is the same problem the rest of the field keeps rediscovering under different names. Anthropic's own long context guidance, OpenAI's notes on attention tradeoffs inside big windows, and Microsoft Research's GraphRAG papers all circle the same fact: a pile of context that only grows, whether it's a system prompt, a vector store, or a knowledge graph, degrades the thing using it, because stale facts sit next to current ones with no signal about which one wins. DeepSeek Harness takes a different structural swing at the same target, building its agent runtime out of swappable plugins so a stale capability gets replaced instead of buried under new instructions.
What strikes me is how little of this is about model capability and how much is housekeeping nobody assigned themselves. Most teams have a deprecation policy for their actual code. Almost nobody has one for the three paragraphs pasted into an agent's instructions eight months ago and never looked at again. How long is your CLAUDE.md, and when did you last delete anything from it?
nitter.gq/suraj_sharma14/status/…
The creator of Claude Code just told everyone to delete their CLAUDE.md.
Not a typo.
Boris Cherny, at YC:
"Every 6 months delete your CLAUDE.md delete your skills, delete your hooks. See what the model does and it might surprise you."
His reasoning:
• Your old rules were fixing weaknesses of older models
• New models don't have those weaknesses anymore
• So your instructions might now be making Claude worse
The method:
1. Delete CLAUDE.md, skills and hooks
2. Work normally and watch where Claude goes off track
3. Add back ONE instruction only when a mistake keeps happening
4. Repeat after every major model release
What to keep:
• Security and compliance rules
• Project quirks Claude can't figure out from the code
What to cut:
• Folder structures, dependency lists, architecture summaries
• Anything Claude can learn by reading your repo
Most people keep adding rules.
The person who built the tool is removing them.
Bookmark this. How long is your CLAUDE.md?
The trick to Vibe Coding is have a bot do it for you. Give #Dots and Muse a full stack plan and tell it to keep prompting the #coding #agent for 24 hours.
The image below is a result of a small prompt sent in the Muse app "Tell Loveable to bolster the RAG DB setup", resulting in a thorough prompt by Muse into the Loveable app.
1
4
103
Open sourced. Added a progress bar with estimate time to complete the current prompt.
github.com/BEXAI/Mod-3-Next-…
1
51
Optinuss retweeted
Introducing Google Pics 🎨 Precise, powerful AI image creation is rolling out now to Google Workspace customers and Google AI Pro & Ultra subscribers.
Google Pics lets you edit individual objects, refine or translate text, and collaborate with your team.
Try it at pics.new.
Ranked in the top 1%, I'm now a Level 5 Master Builder Replit! This is the future of building software. It's been incredible to experience the enhanced agentic AI coding capabilities of this platform as new LLMs get published. This is the future of building software have you tried it yet? replit-certifications.replit…
2
28
What's a "Gauntlet Loop”?
#agentic-#coding technique from #Al investor Matt Shumer (July 27,2026): give an Al agent an ambitious goal plus a concrete 'bar" to beat, let it split the work among sub-agents, and route each piece through a separate critic agent that blind-compares the output to the reference and sends it back until it wins. It's a rebranded, well-executed version of the documented evaluator-optimizer and orchestrator-workers patterns - not a new capability.
3
56












