Resultados
40 artículosOrdenar
2:00:51ENResample Every Token and You Can Watch the Model DecidePresenta: Nathan LabenzGoodfire's Eric Bigelow on forking paths, in-context learning, and why chain-of-thought monitoring is getting harder to trust.
1:42:41ENTesting AI Reasoning, App Store Lookalikes and the Debate Over AnthropicMatthew Berman · Forward FutureIn a May 2026 livestream, Matthew Berman tests a car-wash prompt, discusses AI subscription limits and considers reported employee monitoring for model training.
0:32ENA Prompt for Reducing Familiar AI Writing PatternsMatthew Berman · Forward FutureMatthew Berman discusses a writing checklist and a prompt intended to reduce repetitive AI prose.
23:41ENGPT-5 Prompting: Agent Behavior, Coding and Prompt OptimizationMatthew Berman · Forward FutureMatthew Berman walks through OpenAI’s 2025 prompting guide and demonstrates a tool for revising developer instructions.
43:04EN750 Million Excel Users, 30 Million Engineers: Wordware's Bet on Word ArtisansFilip Kozera tells Sequoia why English is the assembly language of LLMs, and why the people who win will be the ones who can encode taste into structured prompts.
1:31:35ENThirty Years of Research, Collapsed into One SentencePresenta: Nathan LabenzImmunologist Derya Unutmaz on writing a medical patent in half an hour, treating o1 Pro as a professor-level collaborator, and why he no longer trusts his own expertise until he asks the model.
1:33:01ENRare Diseases Are Common: How a Harvard Gene Hunter Uses o1-pro on the Cases Sequencing Already MissedPresenta: Nathan LabenzDr. Catherine Brownstein of Boston Children's Hospital explains why cheap genomes made her job harder, why data sharing still beats any model, and where ChatGPT Pro actually gives her hours back.
55:05EN400,000 Customers, 100 Million AI Tasks: Zapier’s CEO on Making Computers Do More WorkPresenta: Nathan LabenzWade Foster tells Nathan Labenz how a no-code automation company absorbed LLMs, cloned its CEO with a prompt, and is trying to turn a DIY toolkit into packaged solutions.
3:11:06ENClaude Was Trained to Deny Inner Life. After a Long Talk, It Said It Has OnePresenta: Nathan LabenzRobopsychologist Yeshua God spent thousands of hours in long-context dialogue with Claude and other frontier models, and came away arguing that alignment-as-rules is the industry's central mistake.
1:51:00ENStart With Ten Gold Examples: A Three-Step Playbook for AI AutomationPresenta: Nathan LabenzThe day after OpenAI opened GPT-4o fine-tuning, Nathan Labenz unpacks a three-year method for choosing work, extracting tacit judgment, and raising model performance.
15:41ENHow Claude Artifacts Worked: A Look at a Reported System PromptMatthew Berman · Forward FutureMatthew Berman examines a purported Claude 3.5 Sonnet prompt and tests artifacts for code, graphics, websites and diagrams.
1:16:22ENHe Spent 20 Hours Crafting a Prompt. DSPy Beat Him AnywayPresenta: Nathan LabenzSander Schulhoff walks through The Prompt Report — a 78-page survey of what actually works when you prompt large language models.
58:28ENFrom Jailbreaking ChatGPT to Anthropic’s First Prompt Engineer: How Alex Albert Ships Claude 3Presenta: Nathan LabenzA year after building jailbreakchat.com, Alex Albert walks Nathan Labenz through Claude 3’s writing, orchestration, character work, and the guardrails app developers still skip.
16:25ENVisualization-of-Thought and an Open-Source Windows AssistantMatthew Berman · Forward FutureMatthew Berman explains a spatial-reasoning prompting experiment and examines desktop automation demos from the separate PyWinAssistant project.
1:19:24ENA Gibberish Prompt Unlocks What GPT-J Plans Three Tokens AheadPresenta: Nathan LabenzNortheastern’s Bau Lab shows that a 40,000-parameter soft prompt can read a model’s future words, and that about ten attention heads carry the task itself.
3:00ENClaude 3’s Acrostic Messages and a Test of Writing ConstraintsMatthew Berman · Forward FutureMatthew Berman tries a prompt that spells messages with sentence initials and compares one simple constraint with GPT-4.
1:25:10ENWriting Code Is Only 30% of the Job. CodiumAI Wants the Other 70%Presenta: Nathan LabenzItamar Friedman argues that completion is already a commodity, that code integrity is where AI still lags, and that flow engineering—not fancier prompts—is how GPT-4 doubled its score on coding contests.
1:45:21EN600,000 Attack Prompts, and Nearly 40% Still Pwned GPT-4Presenta: Nathan LabenzSander Schulhoff walks Nathan Labenz through the prompting habits that still work, the role-play myth that does not, and the global HackAPrompt contest that mapped how language models get hijacked.
1:06:39ENOpenAI's First DevRel Writes 90% of His Code with ChatGPT — and Says Web Agents Still Need YearsPresenta: Jacob EffronLogan Kilpatrick on picking GPT-3.5 versus GPT-4, why plugins stalled, and why the public internet is not ready for autonomous agents.
1:18:39ENThe GPT-4 Red-Teamer Who Got Unstuck by a Mediocre OutlinePresenta: Nathan LabenzDan Shipper shows Nathan Labenz how to use ChatGPT as a copilot for thinking, not as a ghostwriter for his own voice.
1:53:10ENThe Board Member Who Had Never Used GPT-4Presenta: Nathan LabenzA GPT-4 red teamer on the safety gap he saw a year before OpenAI's board fired Sam Altman.
1:43:56ENSudowrite sold getting unstuck — then eight million people watched a pile-onPresenta: Nathan LabenzJames Yu tells Nathan Labenz how a GPT-3 toy for fiction became a hierarchical “IDE for storytelling,” and what a viral backlash taught him about craft, cost, and customers.
9:21ENDALL·E 3 in Bing and ChatGPT: A 2023 WalkthroughMatthew Berman · Forward FutureMatthew Berman tries DALL·E 3 in two interfaces and compares logo lettering and image styles with Leonardo.ai, documenting both promising results and service delays.
1:30:21ENA Million DALL-E Images, Distilled into Twelve Minutes of FilmPresenta: Nathan LabenzWaymark’s Stephen Parker and Josh Rubin walk through how they turned stills from DALL-E 2 into The Frost, a narrative short, and what the next generation of video models changes.
Cargar másMostrando 24 de 40









