[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]

@dexhorthy Avatar @dexhorthy dex

dex posts on X about ai, compact, agentic, tier the most. They currently have XXXXX followers and XXX posts still getting attention that total XXXXXX engagements in the last XX hours.

Engagements: XXXXXX #

Engagements Line Chart

Mentions: XX #

Mentions Line Chart

Followers: XXXXX #

Followers Line Chart

CreatorRank: XXXXXXX #

CreatorRank Line Chart

Social Influence #

Social category influence technology brands social networks

Social topic influence ai, compact #1706, agentic #48, tier, okta

Top accounts mentioned or mentioned by @humanlayerdev @devgerred @aitinkerers @hellovai @0xblacklight @aidotengineer @claudecode @realshcallaway @cursorai @waldenyan @klarna @karpathy @codebuffai @windsurfai @ampcode @weightsbiases @mattpocockuk @cognition @openai @jeffreyhuber

Top Social Posts #

Top posts by engagements in the last XX hours

"more context engineering == you can ship bigger features in spicier codebases"
X Link @dexhorthy 2025-10-21T23:45Z 6712 followers, 4319 engagements

"Good watch if youre new to context compaction and intentional Md handoffs. IMO compact and handoff are the exact same job to be done but even the different naming is an improvement in the approach to solving - there is no compact there is just create a new context window Weve had /create_handoff and /resume_handoff in codelayer repo for a while and use them quite often. Because codelayer lets you programmatically launch new top level sessions from inside other sessions we also experimented with /continue where the previous thread proposed a prompt and iterates with the user and then launches"
X Link @dexhorthy 2025-10-23T19:34Z 6712 followers, 4439 engagements

"Yes and the worst part about CERTAIN compactors is that the mechanism under the hood is obfuscated from the driver which is ideal for vibe coding but sucks for context engineering"
X Link @dexhorthy 2025-10-26T01:24Z 6712 followers, 1646 engagements

"🦄 ai that works: Ralph Wiggum under the hood with @vaibcode and @GeoffreyHuntley"
X Link @dexhorthy 2025-10-28T17:13Z 6734 followers, 4397 engagements

"raise your hand if youve spent your entire career building software factories"
X Link @dexhorthy 2025-11-03T23:09Z 6735 followers, XXX engagements

"superthread of every resource I have published about advanced claude code usage research-plan-implement and advanced context engineering for coding agents 👇 (mostly chronological)"
X Link @dexhorthy 2025-10-16T04:15Z 6734 followers, 26.2K engagements

"oh fascinating work on context-bench from @charlespacker @sarahwooders My interpretation of context engineering is the code around the model calls. Interesting to see it applied to can models do their own context engineering Feels like this will map somewhat onto conversations in the RAG vs Agentic RAG tier but Im not sure if I ever thought context engineering would be a thing models dofor me CTXE was always about the work the human does to get around the fact that long horizon multi-tool context windows tend to fall off in accuracy fairly quickly I will contemplate this"
X Link @dexhorthy 2025-11-04T01:42Z 6735 followers, 5028 engagements

"how are you testing your ai tools/apps vibes are you subscribed to the eval industrial complex there's been a lot of discussion on the rise of Big Eval and whether its overkill. But also maybe Evals are back come riff with the best builders in the bay at the beautiful Okta HQ in downtown SF - 5:30pm thursday oct 30th"
X Link @dexhorthy 2025-10-24T18:24Z 6715 followers, 8346 engagements

"@clairevo Have seen a few frameworks framed as context engineering tools that just exist to crank out mountains of irrelevant paperwork to make it look like more stuff was done (thereby justifying the existence of/ use of the framework)"
X Link @dexhorthy 2025-11-03T03:48Z 6719 followers, XXX engagements

"@kcosr @andyrewlee i dont think auto compact will out perform a human-in-the-loop compaction. check pinned tweet for more detail"
X Link @dexhorthy 2025-11-03T13:35Z 6721 followers, XX engagements

"holy shit Advanced Context Engineering for Coding Agents is up to 150k views LFG Been an incredible X months collaborating and learning with the entire @humanlayer_dev community to push the limits of what's possible with coding agents"
X Link @dexhorthy 2025-11-01T17:26Z 6734 followers, 15.6K engagements

"hooks skills agents mcp are all different form factors to allow the agent user to engineer the context. But you can do context engineering without them AND the underlying core principles of CTXE and 12-factor agents will let you design up the stack regardless of what model/harness/plugins you go with"
X Link @dexhorthy 2025-11-04T12:49Z 6734 followers, XX engagements

"there's a new concept I'm seeing emerging in AI Agents (especially coding agents) which I'll call "harness engineering" - applying context engineering principles to how you use an existing agent Context engineering - how context (long or short agentic or not) is passed to an LLM to get the best results You do context engineering when you prompt an llm and you do a LOT of context engineering when you design a coding agent harness But there's another layer on top of the core tool-calling orchestration and agentic RAG that happens in the agent. For claude code it's the commands hooks skills"
X Link @dexhorthy 2025-11-04T13:23Z 6735 followers, 7604 engagements