•twitter2798
listening to
timeline
2798
mentions
tracked
tracked
net sentiment
+24%
882 positive
1717 neutral
199 negative
volume & sentiment over time
Sep 30 – Oct 4, 2026 · Daily
sources
most discussed
—
active days
5
mentions
Showing 176–199 of 199 mentions
-
• twitter 2d negativeSomeone introduced me to Synara today: https://t.co/817Lrhjkjz Honestly, never seen a better app to control your AI agents Someone introduced me to Synara today: https://t.co/817Lrhjkjz Honestly, never seen a better app to control your AI agentsview source ↗
-
• twitter 2d negativeYou can use Jev to fix the PII problem in Postgres. To demonstrate that, we built pg_redact: - It simulates a support inbox - Depending on who sees it, a SQL function in Postgres redacts the info https://t.co/IFpi5s0gOz https://t.co/WyfQbLrF1z You can use Jev to fix the PII problem in Postgres. To demonstrate that, we built pg_redact: - It simulates a support inbox - Depending on who sees it, a SQL function in Postgres redacts the info https://t.co/IFpi5s0gOz https://t.co/WyfQbLrF1zview source ↗
-
• twitter 2d negativeI asked Opus 5.5 to visualize the biggest scam in humanity. No words allowed. It gave me this. https://t.co/4i3mCVYQkM I asked Opus 5.5 to visualize the biggest scam in humanity. No words allowed. It gave me this. https://t.co/4i3mCVYQkMview source ↗
-
• twitter 2d negativeOfficial Anthropic tip for Claude Code: stop burning Opus 5.5 context on tasks Sonnet 5.5 can swarm, while Fable 5.1 sits idle spin up an autonomous team with /teams claude --teammates ux,backend,adversary Opus 5.5 acts as the lead architect, scoping architecture and validating pull requests Sonnet 5.5 teammates tak… Official Anthropic tip for Claude Code: stop burning Opus 5.5 context on tasks Sonnet 5.5 can swarm, while Fable 5.1 sits idle spin up an autonomous team with /teams claude --teammates ux,backend,adversary Opus 5.5 acts as the lead architect, scoping architecture and validating pull requests Sonnet 5.5 teammates take isolated git worktrees and hammer out implementations at medium effort Fable 5.1 monitors the peer-to-peer bus as a dedicated adversary, only stepping in at three critical moments: → before a contract locks: does the frontend payload match the backend schema? → when a test breaks twice: are we patching the bug or just hiding the symptom? → before calling done: what attack surface or edge case did everyone overlook? Sonnet 5.5 builds. Fable 5.1 challenges. Opus 5.5 merges and ships Jev engineering runs the identical pattern one layer down: mechanical decisions that need no reasoning (which file to open, which tool to invoke, retry or abort) execute in 16ms, so the frontier models only wake up when execution paths actually diverge Plan on high. Delegate on medium. Keep the adversary on peer-to-peer call. - the full team setup > Opus 5.5 on high coordinates the session and synthesizes PRs > teammate-ux builds client state inside a separate git worktree > teammate-back writes endpoints and handles Redis atomic locks > teammate-adv runs invariant fuzzing and catches replay vulnerabilities > all teammates communicate directly over peer-to-peer messaging without coordinator drag > tasks.json manages file-level mutex locks so nobody steps on another worktree paste the setup and this prompt into Claude Code below: "Configure my Claude Code workspace for autonomous agent teams: 1. Audit ~/.claude/teams and .claude/teams for teammate profiles fitting ux, backend, and adversary > Generate definitions only for missing roles > Pin model: sonnet, effort: medium for workers, and model: fable for adversary > Assign each worker an isolated git worktree branchview source ↗
-
• twitter 2d negativeI usually write for developers but I'm aiming my next post at leaders of companies trying to navigate the change of AI coding agents what's something you wish your leadership would get about agents? or if you're running a company- what problems are you running into? I usually write for developers but I'm aiming my next post at leaders of companies trying to navigate the change of AI coding agents what's something you wish your leadership would get about agents? or if you're running a company- what problems are you running into?view source ↗
-
• twitter 2d negativeDelivering Zomato orders in Indiranagar tonight!!! One guy tipped us ₹200 😭 Book an order now, our paths may cross :p https://t.co/eIAJb054iC Delivering Zomato orders in Indiranagar tonight!!! One guy tipped us ₹200 😭 Book an order now, our paths may cross :p https://t.co/eIAJb054iCview source ↗
-
• twitter 2d negative🚨BREAKING: SoftBank has officially wired its final $10 BILLION into OpenAI Masa had to sell his ENTIRE Nvidia stake to fund the initial payment and was so leveraged it had to issue an $11.1B junk bond to wire this final check SoftBank now owns ~13% of OpenAI https://t.co/DBtqvOroXH 🚨BREAKING: SoftBank has officially wired its final $10 BILLION into OpenAI Masa had to sell his ENTIRE Nvidia stake to fund the initial payment and was so leveraged it had to issue an $11.1B junk bond to wire this final check SoftBank now owns ~13% of OpenAI https://t.co/DBtqvOroXHview source ↗
-
• twitter 2d negativeI’d be issuing an apology to my users if a one person PlanetScale side project caused me to realize my product was slow as fuck and all it took to fix was two weeks of work. Humiliating really. I’d be issuing an apology to my users if a one person PlanetScale side project caused me to realize my product was slow as fuck and all it took to fix was two weeks of work. Humiliating really.view source ↗
-
• twitter 2d negativeThis is why I have a Tesla Y One of the safest car brands and car models I don't trust myself nor anyone else driving so when shit goes down I wanna be in not the prettiest or coolest car, I wanna be in the safest car with the highest survival rate Which all the recent Tesla models are This is why I have a Tesla Y One of the safest car brands and car models I don't trust myself nor anyone else driving so when shit goes down I wanna be in not the prettiest or coolest car, I wanna be in the safest car with the highest survival rate Which all the recent Tesla models areview source ↗
-
• twitter 2d negativewinter arc day 1 >joined gym after lot of thinking ( coz every membership i have taken till date has been waste😭) >set up repo locally , read through loads of documentations https://t.co/sgR6Rr20sg winter arc day 1 >joined gym after lot of thinking ( coz every membership i have taken till date has been waste😭) >set up repo locally , read through loads of documentations https://t.co/sgR6Rr20sgview source ↗
-
• twitter 2d negative"Hey Codex, show me how you'd fix this bug" The new tldraw plugin lets ChatGPT map a problem on the canvas and sketch a few fixes. Comment on the drawing to ask for changes and watch it update live. Here's Max trying it on one of our bugs: https://t.co/OJzLgZtuTC "Hey Codex, show me how you'd fix this bug" The new tldraw plugin lets ChatGPT map a problem on the canvas and sketch a few fixes. Comment on the drawing to ask for changes and watch it update live. Here's Max trying it on one of our bugs: https://t.co/OJzLgZtuTCview source ↗
-
• twitter 2d negativeAlso, 6.1 Sol was our fastest-growing model ever, and was a bit slow under load. Should be much better now! Also, 6.1 Sol was our fastest-growing model ever, and was a bit slow under load. Should be much better now!view source ↗
-
• twitter 2d negativeRT @daxeshpatel: Google's ADK used to pass an agent eval that ran zero cases. 2.10 now errors. Pipelines will go red on upgrade. Don't pin… RT @daxeshpatel: Google's ADK used to pass an agent eval that ran zero cases. 2.10 now errors. Pipelines will go red on upgrade. Don't pin…view source ↗
-
• twitter 2d negative.@clairevo: "We can now ship all our bad ideas. Congratulations!" https://t.co/1Cg4a5D545 .@clairevo: "We can now ship all our bad ideas. Congratulations!" https://t.co/1Cg4a5D545view source ↗
-
• twitter 2d negative@irvinebroque @ghostwriternr THIS SOLVES SO MANY PROBLEMS FOR US @irvinebroque @ghostwriternr THIS SOLVES SO MANY PROBLEMS FOR USview source ↗
-
• twitter 2d negativeDay 274 of road to $30k/mo Only 3 months left in 2026… This year changed my life I went from: - mowing lawns for money - building my first app - failing completely (after months of building 😭) - trying again - scaling my 2nd app to $29k rev in last month All while documenting every single day (which in itself was… Day 274 of road to $30k/mo Only 3 months left in 2026… This year changed my life I went from: - mowing lawns for money - building my first app - failing completely (after months of building 😭) - trying again - scaling my 2nd app to $29k rev in last month All while documenting every single day (which in itself was extremely uncomfortable for me) You can literally change who you are in just a couple of months Don’t give up!view source ↗
-
• twitter 2d negativeThe current situation of developers 💀😭 https://t.co/WX66DoXxXo The current situation of developers 💀😭 https://t.co/WX66DoXxXoview source ↗
-
• twitter 2d negativeRough tier list of free github skills i'd actually install in 2026 https://t.co/X2TLYvVd2o Rough tier list of free github skills i'd actually install in 2026 https://t.co/X2TLYvVd2oview source ↗
-
• twitter 2d negativeatp people are building an ai solution to the tiniest of problems at the speed of light atp people are building an ai solution to the tiniest of problems at the speed of lightview source ↗
-
• twitter 2d negativeAs a Backend Engineer in the AI era, you must build these projects. 1.) High-Concurrency HTTP Server Build: Go or Rust server handling 10k+ concurrent connections with graceful shutdown and backpressure. Why: Concurrency architecture is the one thing AI cannot design for you. 2.) Multi-Tenant Hybrid Search Databas… As a Backend Engineer in the AI era, you must build these projects. 1.) High-Concurrency HTTP Server Build: Go or Rust server handling 10k+ concurrent connections with graceful shutdown and backpressure. Why: Concurrency architecture is the one thing AI cannot design for you. 2.) Multi-Tenant Hybrid Search Database Build: Postgres with Row-Level Security + pgvector + BM25 hybrid ranking across isolated tenants. Why: Structured data and semantic embeddings now share one query engine. 3.) Event-Sourced Order Pipeline Build: Kafka or NATS pipeline with immutable events, dead-letter queues, exactly-once semantics. Why: AI workloads are slow and async. The main thread must never block. 4.) Durable Onboarding Workflow Build: 3-day Temporal workflow with checkpoints, retries and human approval steps. Why: Background jobs are for emails. Durable execution is for multi-step agents. 5.) AI Gateway with Semantic Cache Build: Proxy that caches similar prompts via embeddings, enforces token budgets and fails over to a cheaper model on 503s. Why: The gateway protects your margins and your uptime from flaky, expensive LLM APIs. 6.) PII-Redacting Auth Middleware Build: OAuth2/OIDC provider plus middleware that masks PII before logging and restricts AI agents to read-only DB roles. Why: When agents can write to your database, a prompt injection is a data breach. 7.) Real-Time Streaming Dashboard Build: SSE/WebSocket dashboard streaming LLM tokens and database updates simultaneously with backpressure. Why: Time-To-First-Token and perceived latency are the new UX standards. 8.) Correlated Tracing Pipeline Build: OpenTelemetry + Langfuse pipeline linking each HTTP request to the exact LLM prompt and DB query it triggered. Why: You cannot debug a hallucination without replaying the exact context the model saw. 9.) Ephemeral Environment Provisioner Build: Terraform or Pulumi scripts spinning up a complete isolated staging environment for every pull requeview source ↗
-
• twitter 2d negativePewdiepie casually explained why you should learn coding better than Indian influencers whose entire career is teaching coding😭😭 https://t.co/Y0VueT9F2b Pewdiepie casually explained why you should learn coding better than Indian influencers whose entire career is teaching coding😭😭 https://t.co/Y0VueT9F2bview source ↗
-
• twitter 2d negativeWorking in tech means fumbling generational wealth every few years 😭 https://t.co/IrbuzVVLDr Working in tech means fumbling generational wealth every few years 😭 https://t.co/IrbuzVVLDrview source ↗
-
• twitter 3d negative@IbrahimElkamali Holy shit this is so bad. I’m 3 minutes in and everything he’s saying I’m doing “wrong” is how having a real job worked, even before AI. @IbrahimElkamali Holy shit this is so bad. I’m 3 minutes in and everything he’s saying I’m doing “wrong” is how having a real job worked, even before AI.view source ↗
-
• twitter 3d negativewhat’s happening to chief ai officers 😭 https://t.co/VdlzLHY6Tx what’s happening to chief ai officers 😭 https://t.co/VdlzLHY6Txview source ↗