MEGA (@Megaprompting) header
MEGA (@Megaprompting) profile picture

Prompting is my thing.

Earth
Joined January 2023
Photo by MEGA (@Megaprompting)Photo by MEGA (@Megaprompting)Photo by MEGA (@Megaprompting)Photo by MEGA (@Megaprompting)Photo by MEGA (@Megaprompting)Photo by MEGA (@Megaprompting)Photo by MEGA (@Megaprompting)Photo by MEGA (@Megaprompting)Photo by MEGA (@Megaprompting)Photo by MEGA (@Megaprompting)
MEGA retweeted
Introducing Claude Fable 5.2 and Claude Mythos 5.2, designed to tackle the most daunting technical challenges. They’re capable collaborators on ambitious projects in many fields, and show improvements in areas like coding, reasoning, and vision.
3,177
9,246
6,960
96,260
20,168,427
too much nsl or nah? #IW4L
41
257
18
3,403
119,554
AI HACKERS HAVE PUT SKATEBOARDING IN CALL OF DUTY MODERN WARFARE 2! 🚨 THIS HAS GONE TOO FAR. ITS TIME TO PACE THE FRONTIER. @DarioAmodei @sama @elonmusk @theo
396
2,398
583
29,593
7,521,532
*God when he prompt engineered the sun 🌄*
1
3
258
MEGA retweeted
1,966
3,428
2,449
38,714
11,422,973
You can't displace the normal map (idk what i just said)
7
62
1
1,321
23,431
I still notice confusion here: Ask ☀️Sol to start fresh threads in 🌕Luna. Yes, Sol cannot do Luna subagents by default. So literally ask it to start a thread in Luna, Max effort. Also instruct it to have that output be submitted back to the parent Sol, review it, and if it's not good enough, send it back to the Luna Max thread again. Repeat until output is approved. ☀️Sol -> 🌕Luna 🌕Luna -> ☀️Sol (☀️Sol -> 🌕Luna, 🌕Luna -> ☀️Sol) repeat until mission accomplished.
codex tip: I always use define-goal instead of /goal. It's basically like having a master level genius AI write your goal better than you could. And it's an official OpenAI skill. You can get your prompts to run longer and your output better. Ask a high effort Sol to research + plan it. Sol then spawns a new thread for a workhorse model (Luna Max) to execute the work and return a result to Sol for review. LLM-as-judge to determine if Luna's output is acceptable progress toward goal github.com/openai/skills/blo…
21
9
264
34,262
MEGA retweeted
Counter-Strike 2 - Data Center - de_datacenter Creating a CS2 map with AI
1
1
3
207
Introducing Netherite! Minecraft 1.11.2, rewritten from scratch in C and CUDA, bit-verified against the real game. This is one trained agent playing in it - then the renderer it actually trains through - then 7,200 live worlds stepping in lockstep on one GPU.
156
192
70
4,753
1,437,184
How AI is quietly creating a new digital economy. 
@IrenaCronin and I write this newsletter every week.   AI is creating far more than smarter models. It's giving rise to an entirely new digital economy built on cloud services, infrastructure, AI agents, subscriptions, and compute marketplaces, where the biggest opportunities may come from the businesses that power AI rather than the models themselves. Read and subscribe for free: unaligned.io
23
45
1
99
15,888
Releasing the model weights and technical report of Kimi K3. Kimi K3 is our most capable model: a 2.8T MoE model with native visual understanding and a 1M-token context window. New model architecture: 2.5x the intelligence per unit of compute, not just more params. Alongside Kimi K3, we're opening up more of the stack behind it — high-performance attention kernels, MoE communication library, and infrastructure for running agent environments at scale. Model weights: huggingface.co/moonshotai/Ki… Tech report: github.com/MoonshotAI/Kimi-K… Tech blog: kimi.com/blog/kimi-k3
1,539
7,161
2,352
45,890
14,756,973
MEGA retweeted
We removed ~80% of the Claude Code system prompt for our newest models, this is what we've learned about writing system prompts, skills and Claude.MDs for them.
464
1,897
706
16,314
4,971,652
We've reset 5-hour and weekly rate limits for all users.
3,499
2,963
3,483
47,201
7,450,176
We’ve received notice that the Department of Commerce has lifted export controls on Claude Fable 5 and Mythos 5. We'll begin restoring access tomorrow, and will share an update soon. We’re grateful to our users for their patience, and to everyone who worked with us on redeploying the models.
3,988
12,577
7,034
83,485
15,198,549
Don’t face Sam Altman alone while astral projecting…
186
215
82
3,338
407,723
Replying to @BasedBeff
you cannot outaccelerate me
243
1,032
534
8,734
台風に吸引されるチンパンジーのGIF、汎用性高すぎるwww
156
2,736
153
34,277
1,700,278
can’t be done
NEW: The White House is reportedly demanding Anthropic make Fable 5 impossible to jailbreak before rerelease — which security experts say “can’t be done.”
286
253
53
5,001
289,523
MEGA retweeted
Computer use is now in Claude Code. Claude can open your apps, click through your UI, and test what it built, right from the CLI. Now in research preview on Pro and Max plans.
2,472
4,627
2,796
58,187
16,257,559