AutoGPT

AutoGPT is an open-source "AI agent" that, given a goal in natural language, will attempt to achieve it by breaking it into sub-tasks and using the Internet and other tools in an automatic loop.In addition, AutoGPT maintains short-term memory for the current task, which allows it to provide context to subsequent sub-tasks needed to achieve the larger goal.[10] AutoGPT was used to create ChefGPT, an AI agent able to independently explore the internet to generate and save unique recipes.[4][17] Andrej Karpathy, co-founder of OpenAI which creates GPT-4, further explains that it is AutoGPT's “finite context window” that can limit its performance and cause it to “go off the rails”.[5] Like other autonomous agents, AutoGPT is prone to distraction and unable to focus on its objective due to its lack of long-term memory, leading to unpredictable and unintended behavior.[3] In April 2023, Avram Piltch wrote for Tom's Hardware that AutoGPT 'might be too autonomous to be useful,' as it did not ask questions to clarify requirements or allow corrective interventions by users.For example, one reviewer who tested it on a task of finding the best laptops on the market with pros and cons found that AutoGPT with GPT-4 created a more comprehensive report than one by GPT 3.5.
Developer(s)RepositoryPythonAutonomousartificial intelligencesoftware agentLicenseMIT Licensenatural languageInternetOpenAIGPT-3.5Multi-agent systemsMulti-agent simulationAgent-based computational economicsAgent-based model in biologyAgent-based social simulationAgent-based modeling softwareAgent-oriented programmingAuto-GPTBotnetsPlatforms for software agentsGORITEDistributed artificial intelligenceMulti-agent pathfindingMulti-agent planningMulti-agent reinforcement learningSelf-propelled particlesSwarm roboticshallucinateAndrej KarpathyTom's HardwareClara ShihSalesforceChatGPTArtificial general intelligenceHallucination (artificial intelligence)Toronto StarGitHubin educationDALL-EGitHub CopilotGPT StoreOpenAI FiveSearchGPTWhisperOpenAI CodexGenerative pre-trained transformerGPT-4oSam AltmanremovalMira MuratiEmmett ShearAdam D'AngeloSue Desmond-HellmannPaul NakasoneAdebayo OgunlesiNicole SeligmanFidji SimoLawrence SummersBret TaylorGreg BrockmanReid HoffmanWill HurdHolden KarnofskyElon MuskIlya SutskeverHelen TonerShivon ZilisAI DungeonDeep LearningLangChainMicrosoft CopilotTransformerArtificial intelligence (AI)HistorytimelineParameterHyperparameterLoss functionsRegressionBias–variance tradeoffDouble descentOverfittingClusteringGradient descentQuasi-Newton methodConjugate gradient methodBackpropagationAttentionConvolutionNormalizationBatchnormActivationSoftmaxSigmoidRectifierGatingWeight initializationRegularizationDatasetsAugmentationPrompt engineeringReinforcement learningQ-learningImitationPolicy gradientDiffusionLatent diffusion modelAutoregressionAdversaryUncanny valleySelf-supervised learningRecursive self-improvementWord embeddingHallucinationMachine learningArtificial neural networkLanguage modelLarge language modelAlexNetWaveNetHuman image synthesisSpeech synthesisElevenLabsSpeech recognitionFacial recognitionAlphaFoldText-to-image modelsAuroraFireflyIdeogramMidjourneyStable DiffusionText-to-video modelsDream MachineMusic generationSuno AIWord2vecSeq2seqChinchilla AIClaudeGeminichatbotProject DebaterIBM WatsonIBM WatsonxGranitePanGu-ΣDeepSeekAlphaGoAlphaZeroSelf-driving carMuZeroAction selectionRobot controlAlan TuringWarren Sturgis McCullochWalter PittsJohn von NeumannClaude ShannonMarvin MinskyJohn McCarthyNathaniel RochesterAllen NewellCliff ShawHerbert A. SimonOliver SelfridgeFrank RosenblattBernard WidrowJoseph WeizenbaumSeymour PapertSeppo LinnainmaaPaul WerbosJürgen SchmidhuberYann LeCunGeoffrey HintonJohn HopfieldYoshua BengioLotfi A. ZadehStephen GrossbergAlex GravesAndrew NgFei-Fei LiAlex KrizhevskyDemis HassabisDavid SilverIan GoodfellowNeural Turing machineDifferentiable neural computerVision transformer (ViT)Recurrent neural network (RNN)Long short-term memory (LSTM)Gated recurrent unit (GRU)Echo state networkMultilayer perceptron (MLP)Convolutional neural network (CNN)Residual neural network (RNN)Highway networkAutoencoderVariational autoencoder (VAE)Generative adversarial network (GAN)Graph neural network (GNN)CompaniesProjects