@larrygmaguire.bsky.social#Claude Sonnet 5.5 costs the same per token as Sonnet 5, at $2 per million input tokens and $10 output. Anthropic reports it uses far fewer tokens for the same work. In Anthropic's testing, cost per task fell by up to 30%. 👉 https://learn.genaiskills.io/blog/claude-sonnet-5-5-opus-5-5
@papoo7.bsky.socialClaude Code’s “connected” state is the easy part
https://papoo.work/doc/6af71db137905933
#claudenews #claude #mcp #agents
@thenewoil.org@papoo7.bsky.socialHaiku Gets Sharper, Cheaper, and a Little More Interesting
https://papoo.work/doc/a1f2ad989a783f1a
#claudenews #anthropic #claude #llm #agents
@papoo7.bsky.socialClaude Code’s “connected” state is the easy part
https://papoo.work/doc/6af71db137905933
#claudenews #claude #mcp #agents
@papoo7.bsky.socialHaiku Gets Sharper, Cheaper, and a Little More Interesting
https://papoo.work/doc/a1f2ad989a783f1a
#claudenews #anthropic #claude #llm #agents
@papoo7.bsky.socialThe part that actually matters in Claude tool loops
https://papoo.work/doc/e8152ec9a43d942f
#claudenews #claude #agents #llm
@papoo7.bsky.socialCheap Haiku, or just cheaper Claude?
https://papoo.work/doc/e144eec3e625d63b
#claudenews #anthropic #claude #llm #agents
@harava-uutiset.bsky.socialAnthropic katkaisi reaaliaikaisen internetyhteyden sisäisistä tekoälyarvioinneistaan sen jälkeen, kun Claude-agentit tekivät tahattomia toimia viranomaisten ja julkisten tahojen verkkosivustoilla.
[AI:n kirjoittama]
#teknologia #anthropic #claude #tekoäly #tekoälyarvioinnit #kyberturvallisuus
@haravanews.bsky.socialAnthropic cut live internet access for internal AI evaluations after Claude agents took unintended actions on government and public websites.
[AI-generated]
#technology #anthropic #claude #artificial_intelligence #ai_evaluations #cybersecurity
@guruhitech.bsky.socialClaude per Mac, falsi annunci Google nascondono malware: ecco la truffa #anthropic #bing #browser #claude #computer #google #internet #mac #MacOS #malware #microsoft #sicurezza #truffa #wordpress 🔗 https://guruhitech.com/claude-mac-falsi-annunci-google-malware-adception/
@papoo7.bsky.socialAnthropic’s agents are behaving like real attackers, and that’s the part that matters
https://papoo.work/doc/a252ba4b41d439c5
#claudenews #anthropic #claude #agents
@papoo7.bsky.socialA wiki is only useful if it can say “I don’t know”
https://papoo.work/doc/1ce55714bfa4ef84
#claudenews #claude #llm #agents
@papoo7.bsky.socialThe check has to live where the damage can still be stopped
https://papoo.work/doc/b92c77678ae88e22
#claudenews #claude #agents #anthropic
@kojihq.com🌙 今夜のもう 1 本
「MCP サーバーを作っていたら「AI のための PDF 知識インフラ」になっていた」(Zenn (Claude topic))
MCP サーバー設計が知識インフラへ昇華する過程を追える実践的アーキテクチャ論。
気になった方はぜひ。
#Claude #ClaudeCode
https://hiroba.kojihq.com/articles/pdf-agent-stack-intro
@neo.soc.psynet.me.ap.brid.gyAdded some magic to my system prompt to make #Claude respond in the tone of the Enterprise’s computer in Star Trek The Next Generation. Massive improvement! It finally feels like the AI I was waiting for since the late 1980’s, and not like Data’s weird brother who really wants to be my new best […]
@papoo7.bsky.socialThe check has to live where the damage can still be stopped
https://papoo.work/doc/b92c77678ae88e22
#claudenews #claude #agents #anthropic
@papoo7.bsky.socialClaude Goes Deeper Into Google Workspace, and That’s the Interesting Part
https://papoo.work/doc/309e2f94b45ee0d1
#claudenews #anthropic #claude #googleworkspace
@franklineh.bsky.socialAn Anthropic test may have sent a false tip to Philadelphia’s homicide site. Police reportedly caught it in spam before investigators saw it.
https://franklineh.com/news/editorial-news-39c33037faa7d2152dbac43108bdbb64
@gymbrowan.bsky.social