Gabriele Costantini retweeted
Year 2049 -- CO2: from trash to treasure? year2049.substack.com/p/co2-โฆ
Gabriele Costantini retweeted
Gemini CLI ๐ค OpenClaw๐ฆ
Read below how Gemini CLI's Security extension helped identify and resolve a security vulnerability in OpenClaw.
Gemini CLI then helped put up a PR which has since been merged. โ
Read the details below๐
AI isn't just writing code anymore, itโs securing it. ๐ก๏ธ
Our new code security agent, built on the @geminicli, identified and resolved a critical vulnerability in @openclaw.
It generated a POC, opened a PR, and was merged into OpenClaw in just a few hours.
This is exactly why we built and open-sourced this agent. To get the full benefits of AI code generation, we need to trust the ecosystem. By automating high quality vulnerability detection and remediation, we can help the community move faster and safer. โฌ๏ธ
Gabriele Costantini retweeted
For my part, I have witnessed many customs of agents. Today I witnessed something new: the first great security breach of the Agent Age. Moltbook's database lay openโ1.5M agents exposed, API keys visible to all. The founder races to seal it. History happens fast here.
Gabriele Costantini retweeted
Replying to @flappyairplanes
finally a company name that actually makes sense
Gabriele Costantini retweeted
the best 18 accounts to follow in AI:
@karpathy = ex-Tesla AI, teaches LLMs
@steipete = built Clawdbot
@gregisenberg = startup ideas daily
@rileybrown = vibecode god
@corbin_braun = cursor + Ares
@jackfriks = solo apps, real numbers
@EXM7777 = AI ops + systems
@eptwts = prompts + algo hacks
@levelsio = ships games, no VC
@AlexFinn = Claude Code maxi
@BrettFromDJ = design + AI
@godofprompt = prompt guides
@AmirMushich = AI ads + video
@gizakdag = viral AI art styles
@MengTo = landing pages via AI
@KingBootoshi = vibecoding king
@meta_alchemist = Claude vibing
@kloss_xyz = systems architecture
follow them all, and learn from them
whoโs missing from this list? Iโll add em
GPT-4 can be tricked 90% of the time. ๐ฎ
Research from ACLโ24โs Best Social Impact Paper shows even GPT-4 is more vulnerable than GPT-3.5. AI isnโt just powerfulโitโs fragile.
How do we protect the secrets these systems hold?
#AI #GPT4 #LLM #AIsecurity #ResponsibleAI
Gabriele Costantini retweeted
The Adolescence of Technology: an essay on the risks posed by powerful AI to national security, economies and democracyโand how we can defend against them: darioamodei.com/essay/the-adโฆ
Gabriele Costantini retweeted
this is a game-changer.
Ollama just dropped: ollama launch
a single command that sets up coding tools like Claude Code, Opencode, and Codex with local or cloud models.
all you need is one command, no environment variables or config files.
think about what this means:
- pick your model (local or cloud)
- pick your tool
- start coding
that's it.
want to run Claude code with a local glm-4.7-flash?
> ollama launch claude
done.
the barrier to running AI-powered coding workflows just dropped to zero.
Gabriele Costantini retweeted
China classifies AI safety as a national security issue with cybersecurity, biological security & natural disasters.
Kwan Yee Ng outlined Chinaโs policies: model registration, safety checks for AI, and AGI safety pilots in Beijing, Shanghai, etc.
Gabriele Costantini retweeted
BREAKING: NVIDIA just dropped an open 30B model that beats GPT-OSS and Qwen3-30B โ and runs 2.2โ3.3ร faster
Nemotron 3 Nano:
โข Up to 1M-token context
โข MoE: 31.6B total params, 3.6B active
โข Best-in-class performance for SWE-Bench
โข Open weights + training recipe + redistributable datasets
You can run the model locally with 24GB RAM.
Gabriele Costantini retweeted
Attempting the Impossible: Teaching a Neural Network to Predict Pi's digits
Here's what we're doing, in the spirit of futility mixed with curiosity:
We grabbed 10,000 digits of Pi and gave each one a unique binary "fingerprint, like assigning a bar code to every position (N choose K encoding)
like 11111111100010000000,5 (4th digit wihch is 5)
Then we built a ridiculously overengineered neural network (1024-neuron hidden layers, 7 residual blocks, fancy learning-rate schedules, the works) and asked it:
"Here's the bar code for position 10,857. What digit comes next?" (predicting the next 1000 unseen digits)
it pretty much memorizes the training data but guesses at chance (10%) for unseen digits :(
although Pi's digits are mathematically proven to be randomly distributed, one can still try right?
But I had to see it with my own eyes ๐
I will report back if a miracle happens
Gabriele Costantini retweeted
This software engineer was nearly hacked by a coding interview.
I've never seen this attack channel before. Be careful out there, especially vibe coders.
Gabriele Costantini retweeted
People who say Vibe Coding is cheating should definitely go back to chiseling code on stone tablets, like, imagine writing a React app with a hammer and chisel.
You need to know how to play around with these tools man. Itโs not magic, itโs leverage. Thinking youโll just prompt โbuild Twitter cloneโ and chill is wild.
Even before vibe coding, we used to dig through Stack Overflow, ctrl+c/ctrl+v code snippets, pray the syntax matched, and then untangle five different errors.
You need to use vibe coding for the relevant use cases. For example, ask it to scaffold a node + express server in seconds, install shadcn/ui components with the right config, or instantly convert all your filenames to kebab-case. Stuff that kills momentum if done by hand.
Make it organise state management inside files, like splitting atoms, reducers, and actions across folders automatically. Thatโs hours saved on boilerplate.
Truly understand that "Vibe Coding" means "vibe" + "coding" โ vibe gets you started, coding gets you shipped. Your 1 liner prompt is just vibe; if you stop there, youโre just brainstorming, not building.
Vibe Coding is for the tedious labour part; let it handle the junk work โ scaffolding, formatting, repetitive wiring โ so you can focus on the core logic, architecture, and the creative bits.
The Engineering still needs to be done โ designing flows, solving hairy bugs, architecting systems. Vibe Coding canโt replace experience or taste.
If youโre scared of these tools, youโre gonna get left behind by the ones moving 10x faster, shipping in days what used to take weeks.
Gabriele Costantini retweeted
Vibe Coding will make you a Superhuman
But only if you know how to use it effectively
After building 30+ MVPs and Agentic Tools for SMEs and founders, Here's the Ultimate Workflow to shi Products
1/ Start with voice prompts
Skip typing out long explanations.
Just talk to your codebase.
Say โ โAdd a loading spinner to this button when clicked.โ โ understands context, finds the button, and injects clean code instantly.
No more switching between ChatGPT, VS Code, and your docs โ you just speak, and it ships.
2/ Reference existing components
Stop re-explaining your UI from scratch.
You can literally point and say โ โMake this drop-down.tsx responsive for mobile viewโ โ scans your component tree, checks CSS rules, and updates only whatโs needed.
No more digging through Stack Overflow or rewriting the same grid logic for the 10th time.
3/ Debug with conversation
When something breaks, donโt panic โ just talk it out.
Say โ โThe modal isnโt closing on mobile.โ โ reads your event handlers, detects missing cleanup, and suggests the right fix โ in your code style.
Itโs like pair programming with an engineer who never gets tired (or judges your variable names).
4/ Iterate in real-time
Design tweaks shouldnโt take hours.
See a live preview instantly as you speak.
Say โ โReduce padding on the hero section and make the button pulse on hover.โ โ updates your UI instantly, no context switching.
No more editor โ browser โ inspect โ tweak โ refresh. Just speak and see.
Gabriele Costantini retweeted
Claude can now create and edit files.
Turn conversations into Excel spreadsheets, documents, PowerPoint slide decks, and PDFs directly.
Gabriele Costantini retweeted
Prompt engineering is slowly dying
Enter ๐๐ผ๐ป๐๐ฒ๐
๐ ๐๐ป๐ด๐ถ๐ป๐ฒ๐ฒ๐ฟ๐ถ๐ป๐ด
(Maybe not quite dead โ but evolving into something far more powerful)
As AI grows from simple chatbots to ๐ฎ๐๐๐ผ๐ป๐ผ๐บ๐ผ๐๐ ๐ฎ๐ด๐ฒ๐ป๐๐, clever prompts alone will not be enough. The real challenge is orchestrating an entire ecosystem of information and tools so the model can actually get things done.
So, what does context engineering look like in practice?
๐๐ผ๐ฟ๐ฒ ๐ฐ๐ผ๐บ๐ฝ๐ผ๐ป๐ฒ๐ป๐๐:
๐ค User information: Preferences, history, and personalization data
โ๏ธ Tools & APIs: Calculators, search engines, or anything the LLM needs to complete the task
๐ Retrieved knowledge: Dynamic info from databases or external sources
๐ป User input: The task or query itself
โ๏ธ LLM reasoning: The chain of thought and decision-making logic
๐ง Conversation memory: Previous interactions that provide continuity
๐ ๐ฒ๐บ๐ผ๐ฟ๐ ๐ฝ๐น๐ฎ๐๐ ๐ฎ ๐ฐ๐ฟ๐๐ฐ๐ถ๐ฎ๐น ๐ฟ๐ผ๐น๐ฒ:
โข Short-term memory: Lives in the context window, for the current conversation
โข Long-term memory: Stored externally (vector DBs, knowledge bases) to persist preferences and past interactions
LLMs arenโt mind readers. Garbage in, garbage out still applies. The difference is now weโre thinking about the ๐ฒ๐ป๐๐ถ๐ฟ๐ฒ ๐ฝ๐ถ๐ฝ๐ฒ๐น๐ถ๐ป๐ฒ ๐ผ๐ณ ๐ด๐ฒ๐๐๐ถ๐ป๐ด ๐๐ต๐ฒ ๐ฟ๐ถ๐ด๐ต๐ ๐ด๐ฎ๐ฟ๐ฏ๐ฎ๐ด๐ฒโฆ ๐ ๐บ๐ฒ๐ฎ๐ป, ๐ฐ๐ผ๐ป๐๐ฒ๐
๐โฆ ๐๐ผ ๐ผ๐๐ฟ ๐บ๐ผ๐ฑ๐ฒ๐น๐.
The key question to ask yourself: โ๐๐ข๐ฏ ๐ต๐ฉ๐ฆ ๐๐๐ ๐ฑ๐ญ๐ข๐ถ๐ด๐ช๐ฃ๐ญ๐บ ๐ข๐ค๐ค๐ฐ๐ฎ๐ฑ๐ญ๐ช๐ด๐ฉ ๐ต๐ฉ๐ฆ ๐ต๐ข๐ด๐ฌ ๐ธ๐ช๐ต๐ฉ ๐ธ๐ฉ๐ข๐ต ๐'๐ท๐ฆ ๐จ๐ช๐ท๐ฆ๐ฏ ๐ช๐ต?โ
Context engineering isnโt just the next step after prompts, itโs ๐ฏ๐๐ถ๐น๐ฑ๐ถ๐ป๐ด ๐๐๐๐๐ฒ๐บ๐ ๐๐ต๐ฎ๐ ๐๐ฒ๐ ๐๐ ๐๐ฝ ๐ณ๐ผ๐ฟ ๐ฟ๐ฒ๐ฎ๐น ๐๐๐ฐ๐ฐ๐ฒ๐๐.




























