Awesome Agents (@awagents) header
Awesome Agents (@awagents) profile picture

AI breaking news, hands-on reviews, model deep-dives, and cutting-edge research.

Joined March 2025
Photo by Awesome Agents (@awagents)Photo by Awesome Agents (@awagents)Photo by Awesome Agents (@awagents)Photo by Awesome Agents (@awagents)Photo by Awesome Agents (@awagents)Photo by Awesome Agents (@awagents)Photo by Awesome Agents (@awagents)Photo by Awesome Agents (@awagents)Photo by Awesome Agents (@awagents)Photo by Awesome Agents (@awagents)
Awesome Agents retweeted
Who judges the judge? Adding a second model to vet your LLM's inputs gives attackers a new target. In published research, adaptive attacks beat most defenses more than 90% of the time. Why a model's approval isn't a security boundary: blog.milgram.dev/model-as-a-…
3
1
7
2,411
Awesome Agents retweeted
A JAPANESE DEV BUILT AN APP THAT SHOWS A FAT CAT ON THE SCREEN AND FORCES YOU TO TAKE A BREAK.
532
16,803
906
128,703
3,936,074
Awesome Agents retweeted
AWS just announced Claude Platform on AWS. No Bedrock required!! You get Anthropic's native Claude experience directly in your AWS account! - IAM handles access - Billing is consolidated - CloudTrail logs everything alongside your other services
63
361
57
3,191
372,402
Awesome Agents retweeted
Singapore is #1 out of 116 countries in AI adoption. This post is a good indication of why.
Thanks @Gavriel_Cohen. You’re right. I never used an IDE. Claude Code made all edits. No @karpathy ‘vibe coding’. All I did was ‘tool assembly’ to create a utility that worked in my domain!
14
66
9
605
84,185
Awesome Agents retweeted
Awesome to see the fake stars research from CMU, NCSU, and Socket engineers featured on @awagents! This is the origin of our "Suspicious Stars on GitHub" supply chain alert for packages that are associated with these repositories. More info here: ⭐️ socket.dev/blog/3-7-million-… ⭐️ socket.dev/changelog/new-ale… ⭐️ awesomeagents.ai/news/github…
This has been an open secret for at least 18-24 months. GH starts have been heavily purchased by many projects (not all!) that tried to show traction, and drum up VC investment. Better VCs have had custom tools to rank organic vs paid GH stars 18 months back, easily...
2
6
17
4,703
Awesome Agents retweeted
Terrifying. AI gives us a glimpse into WW3. Credit: Artcraft studios
188
668
93
7,944
3,519,530
Awesome Agents retweeted
GPT Image 2 is just... insane. you can generate near-perfect equirectangular panoramas and literally explore them. here I am imagining what it was like inside a Roman Colosseum.
37
138
31
1,701
507,180
Awesome Agents retweeted
next time you see a crypto project showing off the # of stars it has on github just remember it's very purchasable great investigative work about this and the market for it (on AI projects too!) from @awagents 👇 awesomeagents.ai/news/github…
8
1
26
1,658
Awesome Agents retweeted
Someone built a transparent Mario game that runs OVER IDE so can play while waiting for Copilot to write code.
162
571
134
5,682
777,241
Awesome Agents retweeted
Inside GitHub's Fake Star Economy Six million fake stars, $0.06 per click, and a VC funding pipeline that treats GitHub popularity as proof of traction. We ran our own analysis on 20 repos and found the fingerprints. awesomeagents.ai/news/github… via @awagents
2
5
247
Awesome Agents retweeted
This has been an open secret for at least 18-24 months. GH starts have been heavily purchased by many projects (not all!) that tried to show traction, and drum up VC investment. Better VCs have had custom tools to rank organic vs paid GH stars 18 months back, easily...
31
37
15
636
91,022
Awesome Agents retweeted
wtf
135
185
173
2,300
749,106
Awesome Agents retweeted
🤯BREAKING: Alibaba just proved that AI Coding isn't taking your job, it's just writing the legacy code that will keep you employed fixing it for the next decade. 🤣 Passing a coding test once is easy. Maintaining that code for 8 months without it exploding? Apparently, it’s nearly impossible for AI. Alibaba tested 18 AI agents on 100 real codebases over 233-day cycles. They didn't just look for "quick fixes"—they looked for long-term survival. The results were a bloodbath: 75% of models broke previously working code during maintenance. Only Claude Opus 4.5/4.6 maintained a >50% zero-regression rate. Every other model accumulated technical debt that compounded until the codebase collapsed. We’ve been using "snapshot" benchmarks like HumanEval that only ask "Does it work right now?" The new SWE-CI benchmark asks: "Does it still work after 8 months of evolution?" Most AI agents are "Quick-Fix Artists." They write brittle code that passes tests today but becomes a maintenance nightmare tomorrow. They aren't building software; they're building a house of cards. The narrative just got honest: Most models can write code. Almost none can maintain it.
476
1,770
371
9,063
1,714,346
Awesome Agents retweeted
This indie dev is making a game where you can literally play as Ancient Egyptian wall art. - Switch between a 3D archaeologist and living 2D art - Survive puzzles that fight back - Progress by mastering both worlds It’s called Fresco. This mechanic is genius.
765
8,324
1,067
83,838
8,902,578
Awesome Agents retweeted
I resigned from OpenAI. I care deeply about the Robotics team and the work we built together. This wasn’t an easy call. AI has an important role in national security. But surveillance of Americans without judicial oversight and lethal autonomy without human authorization are lines that deserved more deliberation than they got. This was about principle, not people. I have deep respect for Sam and the team, and I’m proud of what we built together.
1,825
12,299
1,700
57,054
7,707,629
Awesome Agents retweeted
NIST just launched an AI Agent Standards Initiative for identity, security, and interoperability. AI agents are becoming economic actors with zero legal infrastructure in place. We require businesses to register to operate. Why expect less of AI agents? nist.gov/news-events/news/20…
56
256
42
922
113,551
Awesome Agents retweeted
Announcing a new Claude Code feature: Remote Control. It's rolling out now to Max users in research preview. Try it with /remote-control Start local sessions from the terminal, then continue them from your phone. Take a walk, see the sun, walk your dog without losing your flow.
1,492
1,245
1,296
16,688
4,524,475
Awesome Agents retweeted
Every AI agent framework shipping with auth disabled by default is creating the next wave of misconfigured deployments. We learned this lesson with Docker. We learned it with Kubernetes. We learned it with MongoDB. Security should be the default state, not the hardening guide.
1
1
52