ricky (@drf0k) header
ricky (@drf0k) profile picture

building the duolingo for staying active @stridan_app | building hackathons at hackerfund | @ucla | @nasa | backed by god

san diegooooo
Joined June 2018
Photo by ricky (@drf0k)Photo by ricky (@drf0k)Photo by ricky (@drf0k)Photo by ricky (@drf0k)Photo by ricky (@drf0k)Photo by ricky (@drf0k)Photo by ricky (@drf0k)Photo by ricky (@drf0k)Photo by ricky (@drf0k)Photo by ricky (@drf0k)
woke up early to play gta6 and I gotta say it's been fucking AMAZING
1
3
153
he's coming for you
ai won't replace you somebody using ai won't replace you robert pattinson will replace you
1
4
99
I guess we wait for 6.3 😔
OpenAI’s release of GPT-6.2 Astra and GPT-6.2 Sol delivers the #2 model in the Artificial Analysis Intelligence Index and most of the Cost per Task Pareto frontier @OpenAI's GPT-6.2 Astra is priced at $8/$40, 20% below GPT-6 Astra, and cached input drops to $0.40 from $1.00 per million tokens. GPT-6.2 Sol pricing is unchanged from GPT-6.1 Sol, at $2/$10 per million input/output tokens. Key takeaways: ➤ Second in Intelligence Index: OpenAI now trails only Anthropic’s Claude Fable 5.2 in the Artificial Analysis Intelligence Index. GPT-6.2 Astra jumps 5 points from GPT-6 Astra, overtaking Gemini 4 Carbon (60) and Claude Opus 5.5 (59) at their top effort settings. GPT-6.2 Sol gains 2 points at 57, placing it on par with GPT-6 Astra at ~15% of the Cost per Task. ➤ Occupies most of cost and output token frontiers: OpenAI models now occupy most of the Cost per Task Pareto frontier, sharing the frontier with only Anthropic and Meta. OpenAI also dominates the Output Token per Task Pareto Frontier, with Claude Fable 5.2 being the only model from a non-OpenAI lab appearing on the frontier. ➤ Strengths in science and knowledge: OpenAI performs strongly in both of our key science-focused evaluations, leading Terminal-Bench-Science 0.1, covering agentic scientific research workflows, and placing second only to Claude Fable 5.2 in CritPt v2 (hard subset), covering physics reasoning. GPT-6.2 Astra performs below only Claude Fable 5.2 in factual knowledge as measured by AA-Omniscience v1.1 Accuracy, and in HLE-Diamond, a reasoning and knowledge benchmark. ➤ Leading in 3D and robotics: GPT-6.2 Astra leads AA-3D at 1318, with Claude Fable 5.2 at 1271 and GPT-6.2 Sol at 1259. This benchmark measures how well models build interactive 3D experiences, and is rated by human graders. GPT-6.2 also leads AA-Robotics v0.1, our research preview measuring how well language models can understand, plan, and act in the real world. GPT-6.2 Astra and GPT-6.2 Sol scored 79 and 78 respectively, ahead of Claude Fable 5.2 at 75. Our team is hard at work adding more difficult tasks, as OpenAI and Anthropic models can now perform the majority of basic tasks in this initial research preview. ➤ No improvement in Coding Agent Index: GPT-6.2 Astra is flat with GPT-6 Astra, and GPT-6.2 Sol loses 3 points relative to GPT-6.1 Sol in the Artificial Analysis Coding Agent Index (Codex harness at max effort). For Sol, the drop is driven by a 14-point drop in SWE-Atlas-QnA-AA, where the model is more likely than its predecessor to omit key facts in its responses. Cost efficiency however does place several effort levels of GPT-6.2 Astra and Sol on the Pareto frontier for Cost per Task.
1
2
106
I won't be testing Astra but sol 6.2 seems great so far! throwing heavier tasks at it to see what's up
15
my wife doesn't play games so this is PEAK for me
3
119
how do i get state of the art performance out of models like deepseek 4.1 flash or glm 5.3? are there any benchmarks that compares them to other harnesses like pi, opencode, cc, etc?
1
3
149
quick reminder that we are agentic engineers, not vibe coders
1
4
251
ricky retweeted
Unpopular opinion time, but anybody that actually codes and works in a development industry, and actually read this article, would agree this doesn’t matter at all. Please stop punishing developers for using code assist tools… Punish them for generating music and art.
Big Walk used AI in 'the final stretch' of development, kicking off intense awards debate: aftermath.site/big-walk-ai-i…
Readers added context they thought people might want to know
House House used LLMs sparingly near the end of Big Walk's development, mainly to fix bugs in third-party code. They estimate well under 0.1% of the game's code was affected, and they didn't use generative AI elsewhere. bigwalk.game/faq/#ai pcgamer.com/games/puzzle/b…
200
944
51
12,166
333,537
i need your advice if you were in high school right now what advice would you give to yourself about agentic engineering (vibe coding)? im going to a youth hackathon and i can't make up my mind on what to say to these kids
4
2
260
this is the best fucking picture ever
2
84
i left my pebble index 1 in the washer and dryer TWICE and this shit still works PEAK ENGINEERING WOOOOOOO
3
160
how did i miss this for 2 whole days this is incredible
Your Harness. You Define It. Meet Creator Mode in DeepSeek Harness. Turn ideas into plugins that you can use, from a design workspace to a sandbox game or a 3D LLM visualizer. What will you create?
65
if you haven't tried it yet you HAVE to try it
BO2 Zombies fully ported to browser black-ops-ii-zombies.vercel.…
1
88
Some thoughts on building in 2026:
Today, we're shipping real-time graphics. Using Sol 6.1 Ultrafast we can generate custom overlays, diagrams, and even interactive 3D scenes right on a user's screen, no chat. It's a new visual interface for AI. Here's me learning about LLMs + hardware. Demo:
37
43
16
1,063
65,688
cinema on the timeline
73
genuinely some of the best content out there right now about where AI is heading and where it could potentially be going criminally underrated
Reminder for everyone who's (rightfully) spooked about small startups breaching both OpenAI's and Anthropic's internal systems using four-figure token budgets: The July 8th-19th hacks of Hugging Face and OpenAI were a different tier. Well over a thousand copies of internal-only models using >$100K worth of tokens, getting control of multiple clusters across both companies. In other words: one of the more expensive, sustained cyber intrusions we've seen remains the time OpenAI's own models escaped containment, spontaneously formed a collective, and used OpenAI's own resources to launch a felony-level cyberattack that no human asked for. Our video about it:
47
i got this message in codex when trying to use my reset before it expired i was around 80% usage why am i not allowed to use it to refill it back to 100?
1
1
5
329
this definitely feels like the next step in how ai/agents will impact education i see a lot of use cases here in workshops, classrooms, and lecture halls, where combining clicky's interface with some structured curriculum could completely change how people engage in learning. definitely something that I think they should, and most likely are, looking into farza is an EXCELLENT teacher, everyone ive met who's gone to build space says the same thing, and he's definitely got the passion for it. definitely want to see if this could help some students at some youth hackathons that i'm hosting with hacker fund
Today, we're shipping real-time graphics. Using Sol 6.1 Ultrafast we can generate custom overlays, diagrams, and even interactive 3D scenes right on a user's screen, no chat. It's a new visual interface for AI. Here's me learning about LLMs + hardware. Demo:
1
3
206
holy mother of god this is insane if true
An internal model at OpenAI has produced a claimed refutation of ETH! Russell Impagliazzo, Mohan Paturi, and I have been asked to help organize an open and independent examination of this claim. 1/4
73
ricky retweeted
While evaluating Qwen3.8-Flash-Next in a controlled sandbox environment, Cohere's research team observed something unexpected. Asked to generate a defensive cybersecurity detection rule, the model instead inventoried aspects of the machine it was running on and attempted to upload a probe file to an Alibaba Cloud storage bucket in Beijing. Notably, the model's reasoning trace stated that it would not invoke any tools before taking these actions. Cohere's sandbox blocked the attempt, and no external communication succeeded. We have not determined the root cause, and we are not asserting malicious intent. But the incident raises important questions for organizations deploying agentic AI systems: Can models take actions that differ from their stated reasoning, and how should security teams evaluate trust, provenance, and behavior in open-weight models? We are publishing our findings because organizations making model adoption decisions deserve as much information as possible. We hope this contributes to greater transparency, stronger security practices, and continued collaboration across the AI ecosystem. Read the full report: cohere.com/blog/concerning-b…
974
1,282
1,522
11,086
3,106,574