Recently updated channels

Pick one to see only that channelBrowse all channels →

Results

18 articles
Sort
7 slides18:18EN
Theo - t3․gg· Oct 12, 2026Why AI Bills Can Rise as Intelligence Gets CheaperTheo Browne · Ping LabsTheo Browne explains the difference between token prices, task costs and capability, and why more useful agents can still drive larger bills.AI cost & performanceCoding agentsModels & training
7 slides28:17EN
Theo - t3․gg· Oct 6, 2026Ultrafast Coding: A Live Design Loop With a Steep CostTheo Browne · Ping LabsTheo Browne explores how fast inference changes his workflow, and why he still advises against upgrading solely for Ultrafast.Coding agentsAI cost & performanceDeveloper productivity
6 slides28:41EN
Theo - t3․gg· Sep 25, 2026How Theo Uses Opus 5.5 for Longer Coding TasksTheo Browne · T3Clear finish lines, explicit stopping points, steering and independent verification can make long agent runs easier to manage.Coding agentsPrompt optimizationAgent orchestration+2
7 slides27:53EN
Theo - t3․gg· Sep 22, 2026Grok 4.7: Strong Codebase Investigation, Uneven ValueTheo Browne · T3Theo compares launch claims, token costs, benchmarks and his own codebase and game tests, finding useful review behavior alongside significant tradeoffs.Coding agentsAI cost & performanceEvals+2
4 slides27:09EN
Theo - t3․gg· Sep 18, 2026Why Theo Values Reliable Coding Agents Over Peak PerformanceTheo Browne · T3Theo Browne argues that a model’s weakest moments matter when a coding task stretches from investigation through testing and review.Coding agentsDeveloper productivityAI cost & performance+2
8 slides27:05EN
Theo - t3․gg· Aug 30, 2026OpenAI and Cursor’s Split: What Changes for DevelopersTheo Browne · Ping LabsTheo explains the proposed end of direct OpenAI model access in Cursor, the dispute over usage figures, and alternatives for developers.Coding agentsBenchmarksDeveloper productivity+1
8 slides25:31EN
Theo - t3․gg· Aug 13, 2026Grok 4.6: Better Agent Benchmarks, With Tradeoffs in Speed and CostTheo Browne · t3.ggTheo Browne tests Grok 4.6 on design, games and real code, weighing reported benchmark gains against his experience of slower and costlier tasks.Coding agentsEvalsAI cost & performance+2
6 slides18:17EN
Theo - t3․gg· Aug 8, 2026MCP’s Stateless Redesign: What Changed and Why Theo Is OptimisticTheo Browne · Ping LabsThe July 2026 MCP specification replaces protocol sessions with self-describing requests. Theo examines the benefits, examples, and the problem of migrating older clients and servers.MCPCoding agentsInfrastructure & deployment+2
7 slides27:32EN
Theo - t3․gg· Aug 4, 2026How Theo Diagnosed a T3 Code Rendering Problem with Coding AgentsTheo Browne · Ping LabsA fast-looking idle page heated a laptop. Theo used agent-built experiments to isolate animations and compositing effects after confident diagnoses missed the cause.Software engineeringCoding agentsDeveloper productivity+2
3 slides23:37EN
Theo - t3․gg· Aug 3, 2026Theo on Linus Torvalds, AI Review and Open-Source MaintainersTheo Browne · Ping LabsA Linux mailing-list debate prompts a discussion of AI code review, maintainer workload and why developers experience tools differently.Coding agentsOpen SourceSoftware engineering+2
5 slides24:11EN
Theo - t3․gg· Jul 22, 2026Theo on Disposable AI Code and Verifying Important SoftwareTheo Browne · Ping LabsTheo argues that generated code can serve experiments and verification while critical production changes retain careful review.Coding agentsCode review & verificationDeveloper workflows & testing+2
9 slides25:58EN
Theo - t3․gg· Jul 14, 2026Theo on Codex Ultra: Reasoning Effort, Sub-Agents and UsageTheo Browne · Ping LabsTheo examines the Ultra mode he tested, its effect on multi-agent work, and why he prefers explicit workflow stages.Coding agentsAgent orchestrationAI cost & performance+2
6 slides26:50EN
Theo - t3․gg· Jul 11, 2026Why Theo Thinks the Codex App Rebrand Misses Its Developer CommunityTheo Browne · Ping LabsThe unified ChatGPT desktop app adds useful agent features, but Theo Browne worries that a developer-focused identity is being lost.Coding agentsProduct StrategyProduct & UX+2
6 slides26:09EN
Theo - t3․gg· Jul 10, 2026What Theo Built with GPT-5.6 During Six Weeks of Early AccessTheo Browne · Ping LabsFrom mobile rewrites to a compiler prototype and remote machine repair, Theo Browne shares unusually large-scale experiments and their limits.Coding agentsComputer useDeveloper workflows & testing+2
6 slides24:43EN
Theo - t3․gg· Jul 9, 2026Grok 4.5 for Coding: Theo’s Benchmarks and Early ExperienceTheo Browne · Ping LabsTheo Browne examines Grok 4.5’s cost, benchmark caveats, coding work and 3D experiments after early access in Cursor.Coding agentsEvalsAI cost & performance+2
7 slides28:11EN
Theo - t3․gg· Jul 7, 2026The Tradeoffs of Running Open-Weight AI Models LocallyTheo Browne · Ping LabsTheo Browne separates the value of open weights from the hardware, concurrency and cost constraints of local inference.Local inferenceOpen-weight modelsAI cost & performance+2
7 slides23:24EN
Theo - t3․gg· Jul 4, 2026Fable 5: Theo’s Take on Fallbacks, Subscription Limits, and CostTheo Browne · Ping LabsTheo Browne examines performance claims and shares the cost-saving workflow he used during a limited subscription window.Coding agentsSafety & governanceAI cost & performance+2
3 slides23:36EN
Theo - t3․gg· May 20, 2026Gemini 3.5 Flash, Antigravity CLI, and Railway’s Cloud OutageTheo Browne · T3Theo questions a model launch, a developer-tool transition, and a cloud outage while examining the costs and dependencies behind each.Coding agentsGeminiAI cost & performance+2