Eric Khun

6.9K posts

Eric Khun banner
Eric Khun

Eric Khun

@eric_khun

🎮 create your multiplayer game in one click https://t.co/0zB9p5WN82 🛠️ @buffer

🏠 → Katılım Ağustos 2009
596 Takip Edilen1.8K Takipçiler
Eric Khun
Eric Khun@eric_khun·
See what your coding agent is doing in a more visual way
English
0
0
0
31
Eric Khun
Eric Khun@eric_khun·
Start getting some great one shot results, playable, shareable, and multiplayer right away. "Make a game in Taipei 101, where someone with a red tshirt climbs it, and we need to stabilize the building against earthquake."
Eric Khun tweet media
English
0
0
0
47
Eric Khun
Eric Khun@eric_khun·
Just added a real time playground of the game you're making. no more back and forth!
English
0
0
2
104
Eric Khun
Eric Khun@eric_khun·
We have a "fallback" mode when the agent create a game in craftmygame. Users can still edits part of the game it wants, visually and be able to fully control games and graphics and any point.
Eric Khun tweet media
English
0
0
0
73
Eric Khun
Eric Khun@eric_khun·
Not sure what to think about Claude's "forced" 1M context. I was always paranoid to reset context when Opus/Sonnet hit 50% of the 200k window. More context =more hallucinations + more tokens burned. Did they actually solve that? Or do they just want you to spend more tokens?
Eric Khun tweet media
English
0
0
0
104
Eric Khun
Eric Khun@eric_khun·
Been working on adding an AI agent to the CraftMyGame game engine. Soon you'll be able to make a multiplayer game in under 5 minutes, without touching any code. Personalize it for your brand and community, and play it live with friends.
Eric Khun tweet mediaEric Khun tweet media
English
0
0
0
76
Eric Khun
Eric Khun@eric_khun·
pizza leftovers are the best
English
0
0
0
46
Eric Khun
Eric Khun@eric_khun·
Probably why China might get ahead.
Eric Khun tweet media
English
0
0
0
81
Eric Khun
Eric Khun@eric_khun·
This is a new pattern emerging i believe every product sould embrace. let agents decide what they should do inside the app itself. it feels dangerous, but this provides mode delightful experience. just add proper guardrails.
Rohan Paul@rohanpaul_ai

Claude seems to be fixing a super annoying developer problem. Anthropic announced a research preview feature called Auto Mode for Claude Code, expected to roll out by March 12, 2026. The idea is simple: let Claude automatically handle permission prompts during coding so developers don’t have to constantly approve every action. Sstops those annoying permission prompts during long coding sessions. Before this, you had to use `--dangerously-skip-permissions` to work without interruptions. That method worked fine but took away all your safety nets. This new auto mode gives us a smarter option. Claude will take care of the specific permission choices on its own while still blocking threats like prompt injections. You can finally let long tasks run without watching your screen the whole time. Since it is still a research preview, you should run it inside isolated setups like sandboxes or containers for safety. Expect a small jump in token usage and delay, because the model needs extra time to process the security checks. Once available, you just type `claude --enable-auto-mode` to start. If you manage a team and need people to manually approve actions, you can restrict this feature using Mobile Device Management tools like Jamf and Intune or through configuration files.

English
1
1
1
290
Eric Khun
Eric Khun@eric_khun·
@levelsio also they just added back "ultrathink" . try it out , it make it smarter. go figure why they don't make it smarter by default... I think that's why local might win at the end so you can always have the same expected "reasoning" not depending on their will
English
1
0
0
63
@levelsio
@levelsio@levelsio·
Claude Code with Opus 4.6 was so dumb today I finally had to write my own code again A sad state of affairs 🥹
@levelsio tweet media
English
457
23
1.7K
244.4K
Eric Khun
Eric Khun@eric_khun·
@adocomplete what was the effort it was set to before you add it back?
English
0
0
0
27
Ado
Ado@adocomplete·
More info:
Ado tweet media
English
9
1
106
13.2K
Ado
Ado@adocomplete·
Ultrathink is back!
English
156
120
2.3K
228.8K
Morten Just
Morten Just@mortenjust·
it got weird today, but
English
293
395
8.8K
1.6M
Eric Khun
Eric Khun@eric_khun·
Now an official way to manage all Google service via CLI so it's easier for your (openclaw?) agents! Make agents life easier LLM has been trained on hundreds, thousands using cli tools, they instinctively know how to query them
Eric Khun tweet media
English
2
0
1
108
Eric Khun
Eric Khun@eric_khun·
Would be cool if the Claude Code team just open sourced it at this point — if the layer keeps shrinking and it's all JS you can decompile anyway 😄 @trq212 @bcherny @_catwu
English
0
0
0
49
Eric Khun
Eric Khun@eric_khun·
How much do you want to own the agent "harness"? Claude Code team rewrites their harness every month — not because it breaks, but because the model keeps getting smarter and needs less scaffolding and directions. (1/3)
Eric Khun tweet media
English
1
0
0
100