Pinned Tweet
Too many reverse-engineering projects.
Here's mine, just a notepad.exe in rust, same feel, same everything.
github.com/nikkoxgonzales/RE…
this boris guy is tweeting again, must be fable 5.5, he's only noisy when new models comes out.
Agent Skills started as an experiment in Claude Code. Many across the industry have come to adopt it, so we at Anthropic found it more fitting to donate it to the @AgenticAIFdn, next to MCP.
If @bcherny stopped posting and replying, it usually means their model is about to be nerfed. Remember this guy is like Tibo when Opus 5.5 came out. Only @thsottiaux sticks through thick and thin lol.
Nikko retweeted
Today we’re releasing Muse Spark Open, the most capable US open-weight model to date.
Built for coding and agentic work, it excels at long-horizon tasks, complex software engineering, and multi-step reasoning.
Key Model Specs:
→ 816B total / 42B active parameters
→ 1M token context window
→ Natively multimodal across text, image, video, audio
Nikko retweeted
Anthropic released code-modernization v1.0.0, a Claude Code plugin for modernizing legacy codebases
Save this post if you have a legacy project worth modernizing
What I find interesting is that it doesn’t just rewrite code. It tries to prove the new implementation behaves like the original
Here’s how:
- Analyzes the legacy system and extracts business rules
- Generates a modernization plan for your approval
- Rewrites or upgrades the code, even across languages
- Runs the old and new implementations with identical inputs and compares outputs
- Generates additional edge cases to test behavior
- Introduces deliberate bugs to verify tests actually catch them
- Produces a verification report with PROVEN, PARTLY PROVEN, or NOT PROVEN results
It also keeps the original code untouched and requires human approval at critical steps
I think this is the right direction for AI-assisted modernization, generating new code is one thing
Proving that you haven’t broken existing behavior is a completely different challenge
Install:
/plugin install code-modernization@claude-plugins-official
Repo:
github.com/anthropics/claude…
Nikko retweeted
Let's try run Windows XP inside this tweet, tap to open pieter.com/xp/x
Opus 5.5 is better but c'mon GPT 6.1 Sol is still a good model, I find it manageable even in $20 sub.
Buying a good drill from a top-tier brand and using it for the first time feels like using Opus 5.5 for the first time. I didn't expect that!
Nerf Bench from @bridgemindai tracks how much of its launch power every model still has. Every model is within normal variance (±10%) of its launch. bridgebench.ai/nerf-bench
Hermes-Agent is an amazing harness. Ask it to check your email, and even if you have only one unread and it has already read everything, it'll launch a full criminal investigation on all of it. Ten minutes later it'll say, "Hey, you have 1 unread." ask it: "Oh cool, what does it contain?" HA: "Ok, let me do another criminal investigation."